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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     survey
    -0.07
    alarının
    -0.07
     trees
    -0.07
     têm
    -0.06
    solete
    -0.06
     groundwork
    -0.06
    uiten
    -0.06
     recorded
    -0.06
     svého
    -0.06
    ện
    -0.06
    POSITIVE LOGITS
    .black
    0.07
     referee
    0.07
     glyc
    0.07
    中央
    0.06
    NEXT
    0.06
     Luck
    0.06
     argent
    0.06
     περ
    0.06
    чают
    0.06
     متخصص
    0.06
    Act Density 0.004%

    No Known Activations