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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the significance or worth of a situation

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

    auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.78
    rungsseite
    -0.63
     Infór
    -0.62
     Efq
    -0.59
     فريبيس
    -0.59
    ьаж
    -0.58
     myſelf
    -0.58
    ंदीखरीदारी
    -0.57
    RTLU
    -0.55
     Houſe
    -0.55
    POSITIVE LOGITS
     It
    0.40
     it
    0.38
     gi
    0.38
    Vi
    0.36
     is
    0.36
     j
    0.34
     ta
    0.34
     taint
    0.34
     gaz
    0.34
     fi
    0.34
    Act Density 0.387%

    No Known Activations