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

    Neuronpedia

    INDEX
    Explanations

    hacker

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Illustrator
    -0.07
     Wool
    -0.07
    _SQL
    -0.07
    题材
    -0.07
     oil
    -0.07
    Audio
    -0.07
    pto
    -0.07
     Description
    -0.07
    _time
    -0.07
    (Error
    -0.07
    POSITIVE LOGITS
     adher
    0.07
    jab
    0.07
    ستراتيج
    0.07
     şiddet
    0.07
    _machine
    0.07
    התחלה
    0.07
    </
    0.06
    公顷
    0.06
    amentals
    0.06
    .ticket
    0.06
    Act Density 0.005%

    No Known Activations