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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())
    -0.07
    ュー
    -0.07
     当
    -0.07
     données
    -0.06
    _c
    -0.06
    .origin
    -0.06
     nose
    -0.06
    ANJI
    -0.06
     státy
    -0.06
     mensaje
    -0.06
    POSITIVE LOGITS
    %%↵
    0.06
    ‌شن
    0.06
     �
    0.06
    ieri
    0.06
     เซ
    0.06
    associated
    0.06
    Adj
    0.06
             
    0.06
    797
    0.06
    885
    0.06
    Act Density 0.000%

    No Known Activations