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

    Neuronpedia

    INDEX
    Explanations

    code and system commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    薬
    -0.09
     کوم
    -0.08
    อ
    -0.08
    $new
    -0.08
     ڪو
    -0.08
    
    -0.07
     стра
    -0.07
    <iostream
    -0.07
    .visit
    -0.07
     overriding
    -0.07
    POSITIVE LOGITS
     конца
    0.09
     конце
    0.09
     तरफ
    0.08
     нит
    0.08
     duo
    0.08
     partnership
    0.08
     साझ
    0.08
     πλευ
    0.08
     helft
    0.08
     showdown
    0.08
    Act Density 0.002%

    No Known Activations