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

    Neuronpedia

    INDEX
    Explanations

    action, work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     modifier
    -0.07
    �
    -0.07
     Zaman
    -0.06
    Idle
    -0.06
    Canada
    -0.06
     lie
    -0.06
    انگلیسی
    -0.06
     Dubai
    -0.06
    YouTube
    -0.06
     Tru
    -0.06
    POSITIVE LOGITS
    02
    0.07
    าม
    0.06
    _traj
    0.06
    URATION
    0.06
    ‌آ
    0.06
    (ax
    0.05
    ionario
    0.05
     Amit
    0.05
     社
    0.05
    РН
    0.05
    Act Density 0.131%

    No Known Activations