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

    Neuronpedia

    INDEX
    Explanations

    Code and configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pressure
    -0.07
     Ducks
    -0.07
    .jasper
    -0.06
     apprentice
    -0.06
     فوتبال
    -0.06
     cinema
    -0.06
    หย
    -0.06
    \Builder
    -0.06
     Điện
    -0.06
    _noise
    -0.06
    POSITIVE LOGITS
    .StringVar
    0.06
     Mata
    0.06
    ์ได
    0.06
     принадлеж
    0.06
    veled
    0.06
     filib
    0.06
    ])
↵
    0.06
    .visual
    0.06
    %)↵
    0.06
    felt
    0.06
    Act Density 0.215%

    No Known Activations