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

    Neuronpedia

    INDEX
    Explanations

    self-reflection, psychology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Apt
    -0.07
     seguro
    -0.06
     vídeos
    -0.06
    '''
    -0.06
    ocusing
    -0.06
    แกรม
    -0.06
     dự
    -0.06
    Inicio
    -0.06
     simplement
    -0.06
    ัฒนา
    -0.06
    POSITIVE LOGITS
    ACCEPT
    0.07
     UserInfo
    0.07
     wParam
    0.06
    (ray
    0.06
     gut
    0.06
     souls
    0.06
    toBeDefined
    0.06
    (loop
    0.06
     ech
    0.06
     elasticity
    0.06
    Act Density 0.046%

    No Known Activations