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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Expect
    -0.07
     oppress
    -0.07
     przec
    -0.07
     forIndexPath
    -0.07
     �
    -0.07
    Compression
    -0.07
    犹
    -0.06
     الطعام
    -0.06
     exposures
    -0.06
    /fire
    -0.06
    POSITIVE LOGITS
    -mobile
    0.07
     undeniable
    0.07
    AV
    0.07
     habil
    0.07
    מאה
    0.07
    OTO
    0.07
    aru
    0.06
    :'',↵
    0.06
    圓
    0.06
    _inventory
    0.06
    Act Density 0.037%

    No Known Activations