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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .↵↵↵↵↵↵
    -0.07
    tim
    -0.07
    ând
    -0.06
    typeid
    -0.06
     BDSM
    -0.06
     Xavier
    -0.06
     Otto
    -0.06
    =document
    -0.06
    python
    -0.06
     Miner
    -0.06
    POSITIVE LOGITS
     teşekkür
    0.06
     experimented
    0.06
    _PERCENT
    0.06
     نرم
    0.06
     doubling
    0.06
    了一
    0.06
     Laugh
    0.05
     |_
    0.05
     pobl
    0.05
     recycled
    0.05
    Act Density 0.003%

    No Known Activations