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

    Neuronpedia

    INDEX
    Explanations

    cooking recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    domains
    -0.07
     progressively
    -0.07
     Normal
    -0.06
     continuing
    -0.06
     birth
    -0.06
    幾
    -0.06
    _train
    -0.06
               
↵
    -0.06
     wellness
    -0.06
    Hu
    -0.06
    POSITIVE LOGITS
    .'/'.$
    0.07
    leşme
    0.07
    $id
    0.07
     شدن
    0.06
     гориз
    0.06
     prefix
    0.06
    .flow
    0.06
     penc
    0.06
     тест
    0.06
    getState
    0.06
    Act Density 0.157%

    No Known Activations