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

    Neuronpedia

    INDEX
    Explanations

    7

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tel
    -0.09
    咽
    -0.08
     Te
    -0.08
    ]>↵
    -0.07
    requestCode
    -0.07
     )]↵
    -0.07
    聞き
    -0.07
    worked
    -0.07
    )index
    -0.07
     perce
    -0.07
    POSITIVE LOGITS
    Unsafe
    0.07
    Դ
    0.07
     Ways
    0.07
     medida
    0.06
    _analysis
    0.06
     Laden
    0.06
     burgers
    0.06
    两条
    0.06
     Attorney
    0.06
     analytic
    0.06
    Act Density 0.000%

    No Known Activations