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

    Neuronpedia

    INDEX
    Explanations

    direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -lat
    -0.07
     ludicrous
    -0.07
     eins
    -0.07
    组
    -0.06
    -gnu
    -0.06
    ,Object
    -0.06
    Virgin
    -0.06
     annihil
    -0.06
    ’n
    -0.06
    miner
    -0.06
    POSITIVE LOGITS
    creasing
    0.07
     Authority
    0.06
    ")↵↵↵
    0.06
    況
    0.06
    (parts
    0.06
    ornings
    0.06
    ुलन
    0.06
    意见
    0.06
     figuring
    0.06
     abilities
    0.06
    Act Density 0.007%

    No Known Activations