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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WRONLY
    -0.07
     their
    -0.07
    _detected
    -0.06
     lesbienne
    -0.06
     потому
    -0.06
     eins
    -0.06
    Corp
    -0.06
    Linked
    -0.06
     开
    -0.06
    ’яз
    -0.06
    POSITIVE LOGITS
    ef
    0.07
     corrupted
    0.07
    ульт
    0.07
    ीमत
    0.06
    TreeWidgetItem
    0.06
    casting
    0.06
     asphalt
    0.06
    /v
    0.06
     barang
    0.06
    ानसभ
    0.06
    Act Density 0.013%

    No Known Activations