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

    Neuronpedia

    INDEX
    Explanations

    VRAM requirements for models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Training
    0.45
    训练
    0.45
    Predictions
    0.42
     training
    0.41
     Training
    0.41
     predictions
    0.41
    training
    0.40
     artificially
    0.39
    tensorflow
    0.39
     TRAINING
    0.39
    POSITIVE LOGITS
     hoisting
    0.41
     off
    0.40
     Off
    0.39
     በእ
    0.39
     beau
    0.38
    వల
    0.38
     ماضی
    0.38
    𝕤
    0.38
     unloading
    0.38
     കയ
    0.37
    Act Density 0.023%

    No Known Activations