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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Convention
    -0.06
    Home
    -0.06
     heavily
    -0.06
     thang
    -0.06
     ROUT
    -0.06
     pair
    -0.06
     sham
    -0.06
    yah
    -0.06
     posters
    -0.06
     politically
    -0.06
    POSITIVE LOGITS
    ])]
    0.08
    ")
    0.07
    _sig
    0.07
    signals
    0.06
    NotNull
    0.06
    NSMutable
    0.06
    _sell
    0.06
    )=(
    0.06
    ?)
    0.06
     */)
    0.06
    Act Density 0.010%

    No Known Activations