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

    Neuronpedia

    INDEX
    Explanations

    either

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    messages
    -0.07
     sanitary
    -0.06
    attributes
    -0.06
    สร
    -0.06
    gles
    -0.06
    :])↵
    -0.06
     winnings
    -0.06
    fono
    -0.06
     callbacks
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _COMP
    0.07
    十
    0.07
    jící
    0.06
    .SelectCommand
    0.06
    _OCC
    0.06
    -pocket
    0.06
    _MSK
    0.06
     manten
    0.06
    .getClass
    0.06
     odmít
    0.06
    Act Density 0.005%

    No Known Activations