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

    Neuronpedia

    INDEX
    Explanations

    information related to model loading and error handling in programming

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

    Code, training, and model saving/loading

    np_acts-logits-general · gemini-2.0-flash

    training models and loss

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Refuse
    -0.46
    orem
    -0.46
     couvercle
    -0.46
     nonatomic
    -0.45
    xase
    -0.45
     refuse
    -0.43
    ăzi
    -0.42
     room
    -0.42
    Javadoc
    -0.41
    嫁
    -0.41
    POSITIVE LOGITS
     train
    0.84
     trained
    0.83
     training
    0.82
     loss
    0.81
     trainer
    0.77
    train
    0.77
    Train
    0.76
     Train
    0.76
     model
    0.75
     Loss
    0.74
    Act Density 0.335%

    No Known Activations