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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    deny
    -0.07
     withheld
    -0.07
    玩
    -0.07
    GuidId
    -0.06
    알
    -0.06
    奉
    -0.06
     dame
    -0.06
    ォ
    -0.06
     quer
    -0.06
    checker
    -0.06
    POSITIVE LOGITS
     Kenya
    0.08
     specify
    0.07
     overseeing
    0.07
    Для
    0.07
     representative
    0.06
     insurance
    0.06
     immun
    0.06
    _CURRENT
    0.06
    .transport
    0.06
    reduce
    0.06
    Act Density 0.000%

    No Known Activations