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

    Neuronpedia

    INDEX
    Explanations

    Code/writing mistakes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stops
    -0.08
     collaborate
    -0.07
     professors
    -0.07
     precisely
    -0.07
     občan
    -0.07
    擦
    -0.07
    肉
    -0.07
     reconstructed
    -0.07
    ZN
    -0.06
    เฉ
    -0.06
    POSITIVE LOGITS
     Eighth
    0.06
     showDialog
    0.06
    backend
    0.06
    وش
    0.06
     kissing
    0.06
    subplot
    0.06
     Ґ
    0.06
     domů
    0.06
    .record
    0.06
     выпол
    0.06
    Act Density 0.000%

    No Known Activations