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

    Neuronpedia

    INDEX
    Explanations

    expressions related to difficulty or challenge

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

    significantly greater

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zij
    -0.36
     iVar
    -0.35
    going
    -0.34
    loyed
    -0.33
     NSCoder
    -0.33
    yles
    -0.33
    y
    -0.33
     colgante
    -0.33
    corsi
    -0.33
    ter
    -0.33
    POSITIVE LOGITS
    SequentialGroup
    0.63
    льно
    0.62
    fromnode
    0.62
     ainfi
    0.61
     Taktlose
    0.59
    сно
    0.58
    uxxxx
    0.58
    findpost
    0.57
    чно
    0.57
    жно
    0.57
    Act Density 0.006%

    No Known Activations