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

    Neuronpedia

    INDEX
    Explanations

    to/will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ضة
    -0.08
     الخاصة
    -0.07
    דים
    -0.07
    嘴
    -0.07
    alem
    -0.07
    很明显
    -0.07
    wiązan
    -0.07
     premiered
    -0.07
    querque
    -0.07
    民国
    -0.07
    POSITIVE LOGITS
    ATOM
    0.07
     SCORE
    0.07
     gef
    0.07
     FORWARD
    0.07
     Peek
    0.07
    -cross
    0.07
     exped
    0.07
     Jiang
    0.07
     GG
    0.07
    ﺳ
    0.07
    Act Density 0.055%

    No Known Activations