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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ад
    -0.07
    /comment
    -0.07
     Henri
    -0.06
     прок
    -0.06
    udem
    -0.06
     پرد
    -0.06
    istrar
    -0.06
    .im
    -0.06
     品
    -0.06
     Dios
    -0.06
    POSITIVE LOGITS
     якого
    0.07
    accuracy
    0.07
    (UnityEngine
    0.06
    $key
    0.06
    GetMethod
    0.06
     "",↵
    0.06
     recruited
    0.06
    _HEX
    0.06
    _APPLICATION
    0.06
    洋
    0.06
    Act Density 0.001%

    No Known Activations