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

    Neuronpedia

    INDEX
    Explanations

    Software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thes
    -0.07
     fountain
    -0.07
    JoinColumn
    -0.07
     Chad
    -0.07
     Judy
    -0.07
    .r
    -0.06
     forum
    -0.06
     mansion
    -0.06
    orneys
    -0.06
     Navy
    -0.06
    POSITIVE LOGITS
    的局面
    0.07
    Ǯ
    0.07
    STANCE
    0.07
     Púb
    0.06
     rampage
    0.06
    Rol
    0.06
    беж
    0.06
    _CALC
    0.06
     inflicted
    0.06
     postpon
    0.06
    Act Density 0.004%

    No Known Activations