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

    Neuronpedia

    INDEX
    Explanations

    Organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    崎
    -0.06
     swap
    -0.06
    _curve
    -0.06
    онд
    -0.06
    _WRITE
    -0.06
     swaps
    -0.06
    oga
    -0.06
    eksiyon
    -0.06
     Swap
    -0.06
    ạch
    -0.06
    POSITIVE LOGITS
     گرفتن
    0.07
    	IL
    0.07
     ґ
    0.07
    0.07
    '){
↵
    0.07
    )}"↵
    0.07
    0.07
     Fatal
    0.07
     TO
    0.07
     slo
    0.06
    Act Density 0.008%

    No Known Activations