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

    Neuronpedia

    INDEX
    Explanations

    negative numerical values and relates to measurements or quantities

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

    Text following a hyphen

    np_acts-logits-general · gemini-2.0-flash

    numerical ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.69
    Filmografia
    -0.63
    السكان
    -0.55
     care
    -0.55
     CreateTagHelper
    -0.55
     –
    -0.52
    ngdoc
    -0.51
     more
    -0.50
    Rüyada
    -0.50
    heits
    -0.50
    POSITIVE LOGITS
    Personendaten
    0.70
    yntaxException
    0.68
     prefent
    0.63
     itſelf
    0.61
     preſent
    0.59
    헌
    0.59
    DockStyle
    0.59
    ✨:
    0.57
    ?
    0.56
     infinity
    0.55
    Act Density 0.348%

    No Known Activations