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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trash
    -0.07
    ,default
    -0.06
    ISIBLE
    -0.06
    ethe
    -0.06
    oston
    -0.06
    ","\
    -0.06
     modelName
    -0.06
     dla
    -0.06
     Hund
    -0.06
    {j
    -0.06
    POSITIVE LOGITS
     reflex
    0.07
    避
    0.07
    _language
    0.07
     necessarily
    0.06
     handleError
    0.06
     preceding
    0.06
     Reflex
    0.06
    ื้
    0.06
    )↵↵↵↵↵↵
    0.06
    victim
    0.06
    Act Density 0.005%

    No Known Activations