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

    Neuronpedia

    INDEX
    Explanations

    Code/technical discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entityId
    -0.07
     resourceId
    -0.07
     कभ
    -0.06
    ㎡(
    -0.06
     hs
    -0.06
    XObject
    -0.06
     سعود
    -0.06
    уд
    -0.06
    Sean
    -0.06
    ="{{$
    -0.06
    POSITIVE LOGITS
     stacking
    0.07
     distinguish
    0.07
     �
    0.07
     twins
    0.06
     classic
    0.06
     Tie
    0.06
    turn
    0.06
     Κ
    0.06
     Blonde
    0.06
    .forEach
    0.06
    Act Density 0.000%

    No Known Activations