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

    Neuronpedia

    INDEX
    Explanations

    0 or 1

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essays
    -0.07
    Resistance
    -0.06
    을
    -0.06
    자
    -0.06
    Qual
    -0.06
     xem
    -0.06
    REFERRED
    -0.06
     отправ
    -0.06
    On
    -0.06
     traditionally
    -0.06
    POSITIVE LOGITS
     СССР
    0.07
    .Alpha
    0.07
    _HERE
    0.07
    _FILENAME
    0.07
    .CODE
    0.07
    yslu
    0.07
     Caldwell
    0.06
    Buttons
    0.06
    _ACL
    0.06
     म
    0.06
    Act Density 0.003%

    No Known Activations