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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disobed
    -0.07
     Dataset
    -0.07
    _ACT
    -0.07
    .datasets
    -0.06
    REDIT
    -0.06
     Fet
    -0.06
    Youtube
    -0.06
     Sunrise
    -0.06
    .enemy
    -0.06
    abort
    -0.06
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵↵↵↵↵
    0.07
    WARNING
    0.07
    si
    0.07
    :key
    0.06
    Standing
    0.06
     pressing
    0.06
    ↵↵↵
    0.06
     mezi
    0.06
    Outputs
    0.06
    іш
    0.06
    Act Density 0.013%

    No Known Activations