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

    Neuronpedia

    INDEX
    Explanations

    geometric measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旧
    -0.07
    forward
    -0.06
     Breakfast
    -0.06
    _stop
    -0.06
    _builtin
    -0.06
    .First
    -0.06
     Preview
    -0.06
     humano
    -0.06
     самом
    -0.06
    halten
    -0.06
    POSITIVE LOGITS
     tốt
    0.06
    Palindrome
    0.06
     uncomp
    0.06
     розвит
    0.06
    Subscriber
    0.06
    chema
    0.06
    _ROW
    0.05
    ActionTypes
    0.05
     $('<
    0.05
    coord
    0.05
    Act Density 0.018%

    No Known Activations