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

    Neuronpedia

    INDEX
    Explanations

    ben

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    z
    -0.06
    species
    -0.06
    ]]);↵
    -0.06
    лись
    -0.06
     enabled
    -0.06
    =z
    -0.06
    \x
    -0.06
    uz
    -0.06
    _criteria
    -0.06
    ,…↵↵
    -0.06
    POSITIVE LOGITS
    bel
    0.08
    PPER
    0.08
     هم
    0.07
     memcmp
    0.07
     conseils
    0.07
    밍
    0.07
     importantly
    0.07
    ็ว
    0.07
     dem
    0.07
     محل
    0.06
    Act Density 0.003%

    No Known Activations