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

    Neuronpedia

    INDEX
    Explanations

    Answer keys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     التعاون
    -0.09
    طح
    -0.08
    ğraf
    -0.08
    fortawesome
    -0.08
    त्त्व
    -0.08
    ţia
    -0.08
     trabalho
    -0.08
     brink
    -0.08
    цията
    -0.08
    Peripheral
    -0.08
    POSITIVE LOGITS
     cheat
    0.09
     explanations
    0.09
     predetermined
    0.08
    售
    0.08
     commentary
    0.08
     afterwards
    0.08
     reveal
    0.08
    answers
    0.08
    揭秘
    0.08
     체크
    0.08
    Act Density 0.013%

    No Known Activations