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

    Neuronpedia

    INDEX
    Explanations

    terms related to leading and trailing spaces or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    trailing or trails

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.59
    CNP
    -0.48
    évaluateur
    -0.48
    éroport
    -0.46
     OTP
    -0.45
    Portail
    -0.45
    ,:);
    -0.45
    \}=
    -0.44
     quæ
    -0.43
     CNP
    -0.43
    POSITIVE LOGITS
     trailing
    2.05
    trailing
    1.94
    Trailing
    1.66
     trailed
    1.38
    TRAILING
    0.89
     tail
    0.79
     trails
    0.69
    tail
    0.67
     trailers
    0.67
     Tail
    0.66
    Act Density 0.006%

    No Known Activations