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

    Neuronpedia

    INDEX
    Explanations

    asking what"""

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     آنچه
    0.48
     الجميع
    0.40
    究竟
    0.38
     WHAT
    0.37
     everything
    0.35
     чего
    0.34
    เรา
    0.34
    ujesz
    0.33
     हम
    0.33
     بما
    0.32
    POSITIVE LOGITS
     seraient
    0.57
     are
    0.55
     jsou
    0.51
     precautions
    0.50
     waren
    0.48
     byly
    0.47
     were
    0.47
     factors
    0.47
     difficulties
    0.47
     были
    0.46
    Act Density 0.022%

    No Known Activations