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

    Neuronpedia

    INDEX
    Explanations

    row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ché
    -0.07
    atoire
    -0.07
    _TE
    -0.07
    çu
    -0.06
     Clifford
    -0.06
    (nav
    -0.06
    χος
    -0.06
     Authentic
    -0.06
     dans
    -0.06
     LAB
    -0.06
    POSITIVE LOGITS
    Ordinal
    0.06
    543
    0.06
    ropic
    0.06
    orElse
    0.06
    ailing
    0.06
     권
    0.06
    ¬
    0.06
    Obviously
    0.06
    blind
    0.06
     Rogue
    0.06
    Act Density 0.003%

    No Known Activations