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

    Neuronpedia

    INDEX
    Explanations

    expressions of quantity or extent related to emotions, possessions, or values

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

    Follows "how" and precedes comparative words

    np_acts-logits-general · gemini-2.0-flash

    asking how much

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.68
    most
    -0.56
    <bos>
    -0.54
     Most
    -0.52
    Hast
    -0.51
    Most
    -0.50
     most
    -0.50
    ///**
    -0.47
    fier
    -0.47
     méd
    -0.47
    POSITIVE LOGITS
     BoxFit
    0.81
    ftagPool
    0.75
     ComVisible
    0.68
    ItemBackground
    0.67
    معلومات
    0.66
    iggio
    0.66
    multer
    0.66
    бище
    0.66
     estekak
    0.65
    이터
    0.65
    Act Density 0.072%

    No Known Activations