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

    Neuronpedia

    INDEX
    Explanations

    code/settings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pell
    -0.07
    亜
    -0.07
     नर
    -0.06
    (att
    -0.06
    idad
    -0.06
    .Include
    -0.06
    ilent
    -0.06
     mesaj
    -0.06
    ificacion
    -0.06
    Curso
    -0.06
    POSITIVE LOGITS
     […
    0.06
    _fn
    0.06
     UserModel
    0.06
     Epidemi
    0.06
     fint
    0.06
     (){↵
    0.06
     :.:
    0.05
    感情
    0.05
    ADX
    0.05
     medya
    0.05
    Act Density 0.000%

    No Known Activations