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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mex
    -0.07
    inct
    -0.07
    .setTimeout
    -0.07
     MLM
    -0.06
    Ᏼ
    -0.06
     cabeça
    -0.06
     raw
    -0.06
    emb
    -0.06
     assistir
    -0.06
     э
    -0.06
    POSITIVE LOGITS
    !,↵
    0.07
    卺
    0.07
    -variable
    0.06
    TYPES
    0.06
    냔
    0.06
    resizing
    0.06
     vot
    0.06
    档案
    0.06
     loads
    0.06
    غي
    0.06
    Act Density 0.001%

    No Known Activations