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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to financial transactions

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

    Numbers with thousands separated by commas

    np_acts-logits-general · gemini-2.0-flash

    financial figures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.71
     fourteen
    -0.69
     nineteen
    -0.69
     snippetHide
    -0.68
     douze
    -0.64
     fourteenth
    -0.64
     seventeen
    -0.64
     ***!
    -0.64
     eighteen
    -0.64
     المعيارى
    -0.64
    POSITIVE LOGITS
    0
    1.39
    5
    0.66
    8
    0.63
    6
    0.60
    9
    0.59
    1
    0.59
    7
    0.58
    3
    0.56
    2
    0.56
    4
    0.54
    Act Density 0.044%

    No Known Activations