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

    Neuronpedia

    INDEX
    Explanations

    the word "unless" and its variations

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

    unless exceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.56
    endphp
    -0.55
     GoogleFonts
    -0.54
    -0.52
     виправивши
    -0.49
    odeon
    -0.49
    utenant
    -0.49
    Controllo
    -0.48
    netje
    -0.47
    codename
    -0.46
    POSITIVE LOGITS
    Unless
    2.05
     Unless
    2.03
     unless
    1.80
    unless
    1.70
    除非
    1.17
     kecuali
    0.83
     sauf
    0.78
     Except
    0.73
    Except
    0.71
     except
    0.65
    Act Density 0.006%

    No Known Activations