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

    Neuronpedia

    INDEX
    Explanations

    acting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _submenu
    -0.08
     partir
    -0.07
     nast
    -0.07
     Ferr
    -0.06
    perfil
    -0.06
     кл
    -0.06
    Procedure
    -0.06
    agement
    -0.06
    anism
    -0.06
     Hat
    -0.06
    POSITIVE LOGITS
     reasoning
    0.07
    AYS
    0.07
     شب
    0.07
    …..
    0.06
    logger
    0.06
     distribution
    0.06
    ايد
    0.06
    ??
    0.06
    graphs
    0.06
    baseUrl
    0.06
    Act Density 0.001%

    No Known Activations