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

    Neuronpedia

    INDEX
    Explanations

    T

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     radioButton
    -0.07
    Picture
    -0.07
    _SHARE
    -0.07
     Мор
    -0.06
    (pass
    -0.06
    状況
    -0.06
    ogie
    -0.06
    一度
    -0.06
    银
    -0.06
    奧
    -0.06
    POSITIVE LOGITS
     interrupts
    0.07
    .message
    0.06
     neob
    0.06
     имп
    0.06
     infections
    0.06
     Infect
    0.06
    τα
    0.06
    .T
    0.06
     europe
    0.06
     responding
    0.06
    Act Density 0.015%

    No Known Activations