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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Do
    -0.08
    iče
    -0.07
     crust
    -0.07
    jQuery
    -0.07
    圧
    -0.06
     protection
    -0.06
     Ya
    -0.06
     predicts
    -0.06
     Restaurant
    -0.06
    .If
    -0.06
    POSITIVE LOGITS
     toReturn
    0.08
    608
    0.07
    808
    0.07
    .ByteString
    0.07
    _OPTION
    0.06
     Rigidbody
    0.06
     \
    0.06
     Constructors
    0.06
    sts
    0.06
    ━━
    0.06
    Act Density 0.046%

    No Known Activations