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

    Neuronpedia

    INDEX
    Explanations

    versus, vs, between contrasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thậm
    0.43
     pokud
    0.41
     шпански
    0.41
     ભાગ
    0.39
    ન્દ
    0.38
     ника
    0.38
     никаких
    0.37
     żad
    0.37
     RCLCPP
    0.37
    如果有
    0.36
    POSITIVE LOGITS
     versus
    1.32
     vs
    1.19
    vs
    1.00
     बनाम
    1.00
    versus
    0.95
     Vs
    0.90
     Versus
    0.86
     VS
    0.78
    VS
    0.68
    Vs
    0.64
    Act Density 0.168%

    No Known Activations