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

    Neuronpedia

    INDEX
    Explanations

    Vill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     East
    -0.08
     Goldberg
    -0.07
     Bulgarian
    -0.07
     Christian
    -0.07
     kla
    -0.07
     cd
    -0.06
     Asia
    -0.06
     earth
    -0.06
    aku
    -0.06
     Coff
    -0.06
    POSITIVE LOGITS
    .InnerException
    0.07
     نفر
    0.07
    ил
    0.07
     timelines
    0.07
    ivent
    0.07
     tìm
    0.06
     vài
    0.06
     typically
    0.06
     strtotime
    0.06
    iola
    0.06
    Act Density 0.002%

    No Known Activations