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

    Neuronpedia

    INDEX
    Explanations

    references to sleep patterns and alarm functionalities

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

    waking up early and late

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.41
     intptr
    -0.40
    oura
    -0.39
    Havolalar
    -0.39
    itespace
    -0.39
    stalt
    -0.38
    ssohn
    -0.38
    illons
    -0.38
    yszcz
    -0.38
     Nantes
    -0.37
    POSITIVE LOGITS
    posedge
    0.50
     curfew
    0.49
     autorytatywna
    0.49
     escuelas
    0.47
     tomorrow
    0.47
     papá
    0.46
     nocturno
    0.45
     eléctrico
    0.45
     mamá
    0.44
    ̈́
    0.44
    Act Density 0.012%

    No Known Activations