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

    Neuronpedia

    INDEX
    Explanations

    .compile

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kurz
    -0.07
    rx
    -0.07
    .value
    -0.07
    mitted
    -0.06
     priests
    -0.06
    mutation
    -0.06
    .previous
    -0.06
    ox
    -0.06
     Decay
    -0.06
     bana
    -0.06
    POSITIVE LOGITS
    ンジ
    0.07
     getArguments
    0.07
    _eff
    0.06
    _PO
    0.06
    ارات
    0.06
    bron
    0.06
    ltra
    0.06
    -invalid
    0.06
     DAN
    0.06
    Meteor
    0.06
    Act Density 0.010%

    No Known Activations