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

    Neuronpedia

    INDEX
    Explanations

    face

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extinct
    -0.08
     titan
    -0.07
    oze
    -0.07
    引
    -0.07
    flush
    -0.07
     집
    -0.07
     hava
    -0.07
    Lets
    -0.07
    veis
    -0.07
     Mun
    -0.06
    POSITIVE LOGITS
    rief
    0.07
    oss
    0.06
    Actual
    0.06
    永久
    0.06
    .obtain
    0.06
    แน
    0.06
     reasonably
    0.06
     commentaire
    0.06
     Rural
    0.06
    Wednesday
    0.06
    Act Density 0.002%

    No Known Activations