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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pete
    -0.07
     itch
    -0.06
    _generic
    -0.06
     boxed
    -0.06
    OWN
    -0.06
    ворю
    -0.06
    Sign
    -0.06
     food
    -0.06
    enção
    -0.06
    ีส
    -0.06
    POSITIVE LOGITS
     dedim
    0.07
    .Categories
    0.07
    xmm
    0.06
     наруш
    0.06
     intValue
    0.06
    bies
    0.06
    :::::|
    0.06
    .ModelAdmin
    0.06
     zatím
    0.06
    enties
    0.06
    Act Density 0.020%

    No Known Activations