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

    Neuronpedia

    INDEX
    Explanations

    Numbers in lists/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pg
    -0.08
    appers
    -0.08
     να
    -0.08
    .Det
    -0.08
    PG
    -0.08
    .‏
    -0.08
     —↵↵
    -0.08
     sor
    -0.08
     PG
    -0.08
     puls
    -0.07
    POSITIVE LOGITS
     företag
    0.08
    мот
    0.08
     Unternehmen
    0.08
    _allow
    0.07
     insisted
    0.07
     મં
    0.07
     kampuni
    0.07
    aird
    0.07
     excluded
    0.07
     verpflicht
    0.07
    Act Density 0.002%

    No Known Activations