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

    Neuronpedia

    INDEX
    Explanations

    measurements and quantities in various contexts, particularly involving time, weight, and dimensions

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

    numbers and fractions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.71
    antaranya
    -0.49
    ocrine
    -0.48
    msgTypes
    -0.48
    GOTREF
    -0.47
    few
    -0.46
    ndata
    -0.45
    orice
    -0.45
    loo
    -0.44
    viele
    -0.44
    POSITIVE LOGITS
     Walkover
    0.44
     kasarigan
    0.42
    Sinopse
    0.38
    FixedSize
    0.37
     rett
    0.32
    Skocz
    0.32
     student
    0.32
     morceau
    0.31
     Rimini
    0.31
    انتهای
    0.31
    Act Density 0.088%

    No Known Activations