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

    Neuronpedia

    INDEX
    Explanations

    changes in state

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /site
    -0.07
    Aura
    -0.07
    less
    -0.07
    .lex
    -0.06
     β
    -0.06
    Composer
    -0.06
    _In
    -0.06
     attacking
    -0.06
    wi
    -0.06
    gart
    -0.05
    POSITIVE LOGITS
    :semicolon
    0.07
    čer
    0.07
     Specify
    0.07
     Emerging
    0.07
    TEMPL
    0.07
     harb
    0.07
     nond
    0.06
     complying
    0.06
     �
    0.06
    _pd
    0.06
    Act Density 0.251%

    No Known Activations