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

    Neuronpedia

    INDEX
    Explanations

    say commands

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .vert
    -0.06
    Office
    -0.06
    .CREATED
    -0.06
    基础
    -0.06
    (Fl
    -0.06
     Diğer
    -0.06
     paced
    -0.06
     موارد
    -0.06
     merged
    -0.06
    َه
    -0.06
    POSITIVE LOGITS
     ALSO
    0.07
    of
    0.06
    ToF
    0.06
    /Login
    0.06
     commande
    0.06
    .Alpha
    0.06
    pard
    0.06
     zeměděl
    0.06
    -С
    0.06
     conven
    0.06
    Act Density 0.017%

    No Known Activations