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

    Neuronpedia

    INDEX
    Explanations

    purchase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    응
    -0.06
     mek
    -0.06
    頓
    -0.06
    ikat
    -0.06
    Setting
    -0.06
    tica
    -0.06
     kcal
    -0.06
    ceae
    -0.06
     meme
    -0.06
     mega
    -0.06
    POSITIVE LOGITS
     staff
    0.07
    İng
    0.07
     Grey
    0.07
     Chi
    0.06
    Jobs
    0.06
     berries
    0.06
     Staff
    0.06
     servants
    0.06
     __________________________________
    0.06
    _sk
    0.06
    Act Density 0.011%

    No Known Activations