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

    Neuronpedia

    INDEX
    Explanations

    defining width and height

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inboard
    0.39
    adple
    0.38
     iphdr
    0.38
     yaklaşık
    0.37
    LookAndFeelInfo
    0.37
     ode
    0.36
     کوم
    0.35
     comunità
    0.35
    Од
    0.35
     ഏക
    0.34
    POSITIVE LOGITS
    match
    0.55
     Match
    0.54
    MATCH
    0.54
    Match
    0.50
    full
    0.48
     full
    0.47
     match
    0.45
     मैच
    0.45
     MATCH
    0.44
     FULL
    0.43
    Act Density 0.004%

    No Known Activations