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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /category
    -0.08
    MessageType
    -0.07
    ognition
    -0.06
     восп
    -0.06
     примерно
    -0.06
     دور
    -0.06
     campaigned
    -0.06
     fread
    -0.06
    Fake
    -0.06
     브라
    -0.06
    POSITIVE LOGITS
    ặc
    0.06
    ってい
    0.06
     ﺍ
    0.06
     CPUs
    0.06
    _actions
    0.06
    .NULL
    0.06
    _Update
    0.06
     eo
    0.06
     things
    0.06
     alk
    0.06
    Act Density 0.074%

    No Known Activations