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

    Neuronpedia

    INDEX
    Explanations

    Brevity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     proceedings
    -0.08
    .identifier
    -0.07
    woord
    -0.07
    лож
    -0.06
    вар
    -0.06
    aph
    -0.06
     caveat
    -0.06
    -src
    -0.06
    pieces
    -0.06
     Budget
    -0.06
    POSITIVE LOGITS
     희
    0.06
    .manage
    0.06
     implode
    0.06
     Struct
    0.06
     "[%
    0.06
    populate
    0.06
    (Runtime
    0.06
     occupying
    0.06
    ()},
    0.06
    purchase
    0.06
    Act Density 0.003%

    No Known Activations