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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Great
    -0.07
    ystems
    -0.07
     walls
    -0.06
    /business
    -0.06
    ารณ
    -0.06
    oreal
    -0.06
    .")↵↵
    -0.06
    Ol
    -0.06
    )?↵↵
    -0.06
     unreal
    -0.06
    POSITIVE LOGITS
     зали
    0.07
    >Lorem
    0.07
     exhilar
    0.07
    ılığıyla
    0.06
     navr
    0.06
     gerekli
    0.06
     SELECT
    0.06
     ori
    0.06
    cls
    0.06
    ／／
    0.06
    Act Density 0.003%

    No Known Activations