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

    Neuronpedia

    INDEX
    Explanations

    expressions of confusion or disbelief related to understanding or comprehending situations

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

    cannot understand or imagine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.57
    complexContent
    -0.50
    FDRE
    -0.47
     linkovi
    -0.41
    ніципа
    -0.41
    InstrumentedTest
    -0.39
    حوالہ
    -0.39
     dangers
    -0.38
     Bioaccumulative
    -0.38
    Rujuakan
    -0.37
    POSITIVE LOGITS
     myſelf
    0.64
     defaultstate
    0.60
    Cannot
    0.53
     leaſt
    0.52
     regret
    0.51
     reaſon
    0.51
    Regret
    0.48
     imagui
    0.48
    ðsíða
    0.48
     Regret
    0.47
    Act Density 0.013%

    No Known Activations