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

    Neuronpedia

    INDEX
    Explanations

    .html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sanctuary
    -0.08
     חינם
    -0.07
    (Command
    -0.06
     Cá
    -0.06
     dormant
    -0.06
    <Data
    -0.06
    炱
    -0.06
    ategoria
    -0.06
    にある
    -0.06
     attending
    -0.06
    POSITIVE LOGITS
     Prot
    0.07
    soles
    0.07
    Checkbox
    0.07
     prob
    0.07
     boobs
    0.07
    雇
    0.07
    ∏
    0.07
    onclick
    0.07
     sola
    0.07
    really
    0.07
    Act Density 0.003%

    No Known Activations