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

    Neuronpedia

    INDEX
    Explanations

    domain extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Creek
    -0.08
    =float
    -0.07
    قيد
    -0.07
    clist
    -0.07
    Cleanup
    -0.07
    关系
    -0.07
    兆
    -0.07
    _LONG
    -0.07
    ении
    -0.07
    IPv
    -0.06
    POSITIVE LOGITS
    okane
    0.07
     Pages
    0.07
    ourse
    0.07
    🖇
    0.07
     ADA
    0.07
    contract
    0.07
    層
    0.06
    arkan
    0.06
    rowsing
    0.06
    薷
    0.06
    Act Density 0.007%

    No Known Activations