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

    Neuronpedia

    INDEX
    Explanations

    questioning phrases or expressions of uncertainty

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

    questions about questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.64
    rungsseite
    -0.55
     الرياضيه
    -0.53
     <=",
    -0.53
     Administrativna
    -0.52
    elemField
    -0.52
    MemoryWarning
    -0.51
     فريبيس
    -0.49
    AISSEE
    -0.49
     MainAxisSize
    -0.49
    POSITIVE LOGITS
     بخ
    0.44
    溯
    0.43
    +#+#
    0.43
     surla
    0.39
    hadur
    0.38
    pantalón
    0.37
    ValueStyle
    0.36
    lanations
    0.36
    owulf
    0.36
    νή
    0.35
    Act Density 0.034%

    No Known Activations