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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lazy
    -0.07
     реч
    -0.07
    theorem
    -0.06
    dest
    -0.06
    šk
    -0.06
    marca
    -0.06
    (rate
    -0.06
    .toLowerCase
    -0.06
     kims
    -0.06
     Erin
    -0.06
    POSITIVE LOGITS
    ením
    0.07
     Beit
    0.06
     JVM
    0.06
     ACCEPT
    0.06
     перед
    0.06
    OD
    0.06
     Kurulu
    0.06
    них
    0.06
    ой
    0.06
    _();↵
    0.06
    Act Density 0.000%

    No Known Activations