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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mont
    -0.07
    (selection
    -0.06
    '|
    -0.06
    ús
    -0.06
    just
    -0.06
     jig
    -0.06
    41
    -0.06
    amide
    -0.06
    PR
    -0.06
     twe
    -0.06
    POSITIVE LOGITS
    .WEST
    0.07
    णन
    0.07
    ีอย
    0.07
     Huyện
    0.07
    ละ
    0.06
     Genuine
    0.06
     davranış
    0.06
    _GRA
    0.06
     společ
    0.06
     hizo
    0.06
    Act Density 0.039%

    No Known Activations