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

    Neuronpedia

    INDEX
    Explanations

    instances of frustration or confusion related to problem-solving

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

    figure out or seem to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.69
    Gambas
    -0.68
     فريبيس
    -0.60
    XmlAccessorType
    -0.59
     ostavi
    -0.57
     nakalista
    -0.56
    eradish
    -0.52
     الرياضيه
    -0.51
    StoryboardSegue
    -0.49
     förr
    -0.49
    POSITIVE LOGITS
    fig
    0.41
     Fig
    0.39
    Fig
    0.38
    flat
    0.36
     Figure
    0.36
    diffic
    0.36
    Figure
    0.36
     difficulty
    0.35
     CRED
    0.35
    ľ
    0.35
    Act Density 0.051%

    No Known Activations