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

    Neuronpedia

    INDEX
    Explanations

    IF function call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vection
    0.39
    oresizing
    0.38
     junk
    0.37
    junk
    0.36
    ಿಕೊಂಡ
    0.36
     AnyObject
    0.36
     van
    0.35
     লিংক
    0.35
    つけた
    0.34
    闌
    0.34
    POSITIVE LOGITS
     conditions
    0.55
     conditional
    0.55
    条件
    0.54
     услови
    0.53
     conditionally
    0.53
    OrElse
    0.52
    條件
    0.52
     ifelse
    0.52
    Conditional
    0.52
    conditionals
    0.50
    Act Density 0.009%

    No Known Activations