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

    Neuronpedia

    INDEX
    Explanations

    inhibition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    フト
    -0.07
    no
    -0.07
    дии
    -0.07
    rious
    -0.06
     yt
    -0.06
    wendung
    -0.06
    ۲۰
    -0.06
    elon
    -0.06
     Switch
    -0.06
     registros
    -0.06
    POSITIVE LOGITS
     cx
    0.07
    .AutoScaleMode
    0.06
    ˜
    0.06
     getChild
    0.06
    晴
    0.06
     Restr
    0.06
    ayo
    0.06
     adjacency
    0.06
     families
    0.06
     vic
    0.06
    Act Density 0.026%

    No Known Activations