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

    Neuronpedia

    INDEX
    Explanations

    She

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oklahoma
    -0.06
    メリカ
    -0.06
     نامه
    -0.06
     이용
    -0.06
    ERICA
    -0.06
    --------------------------------
    -0.06
     وه
    -0.06
    IFIED
    -0.06
     安
    -0.06
    %H
    -0.05
    POSITIVE LOGITS
    -proof
    0.07
    /file
    0.07
    _graph
    0.07
    bos
    0.07
     motif
    0.07
     halde
    0.06
     WebSocket
    0.06
    Vintage
    0.06
     Suffolk
    0.06
     شخصية
    0.06
    Act Density 0.033%

    No Known Activations