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

    Neuronpedia

    INDEX
    Explanations

    confidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continua
    -0.08
     kennen
    -0.07
    _ACTIV
    -0.06
    tim
    -0.06
     Shore
    -0.06
    اص
    -0.06
    getPost
    -0.06
    gew
    -0.06
    ivol
    -0.06
    ndl
    -0.06
    POSITIVE LOGITS
    asmine
    0.06
     initialization
    0.06
     Daha
    0.06
     Published
    0.06
    있는
    0.06
    ��
    0.06
    .AllowUser
    0.06
    andoned
    0.06
     Usa
    0.06
    (src
    0.06
    Act Density 0.001%

    No Known Activations