Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluation metrics and loss functions in machine learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    CNN, classification, and prediction

    np_acts-logits-general · gemini-2.0-flash

    classification score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     welcome
    -0.47
    rung
    -0.43
    Install
    -0.42
     installations
    -0.42
    welcome
    -0.42
    Initializable
    -0.42
    Fractal
    -0.42
     iniziale
    -0.41
     tred
    -0.41
     zim
    -0.40
    POSITIVE LOGITS
     prediction
    0.99
     predictions
    0.99
     predicted
    0.97
     Prediction
    0.91
     predict
    0.90
     Predicted
    0.87
     Predictions
    0.85
     labels
    0.84
     predicts
    0.83
     predicting
    0.82
    Act Density 0.293%

    No Known Activations