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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Metrics
    -0.07
    Nm
    -0.07
    _uid
    -0.07
    êm
    -0.07
    36
    -0.07
    ану
    -0.06
    .cor
    -0.06
    eller
    -0.06
    Operations
    -0.06
     converting
    -0.06
    POSITIVE LOGITS
    —
    0.06
     Dancing
    0.06
    --+
    0.06
     waitress
    0.06
     enactment
    0.06
    JEXEC
    0.06
    ampler
    0.06
    argon
    0.06
    ných
    0.06
     Slash
    0.06
    Act Density 0.022%

    No Known Activations