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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sampling
    -0.07
    atitude
    -0.07
     gestures
    -0.07
    _nums
    -0.07
    メント
    -0.07
    -saving
    -0.06
    άκ
    -0.06
    ลด
    -0.06
    dogs
    -0.06
     Commands
    -0.06
    POSITIVE LOGITS
    Gab
    0.07
     "'.
    0.07
     Gab
    0.06
    }".
    0.06
     milion
    0.06
     cent
    0.06
    \x
    0.06
    .strip
    0.06
    istle
    0.06
     k
    0.06
    Act Density 0.031%

    No Known Activations