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

    Neuronpedia

    INDEX
    Explanations

    и эффектив

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ק
    0.46
    וד
    0.46
    ofthe
    0.45
    .$,
    0.45
    arter
    0.42
    ISE
    0.42
     Climb
    0.42
    Sar
    0.42
    perl
    0.41
    र्नल
    0.41
    POSITIVE LOGITS
            
    0.51
    ja
    0.50
    ún
    0.50
    ao
    0.49
    ais
    0.48
    ক্ষা
    0.47
     UIApplication
    0.46
     お客様
    0.46
    背
    0.46
    ková
    0.45
    Act Density 0.000%

    No Known Activations