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

    Neuronpedia

    INDEX
    Explanations

    statistical data and metrics related to economic and job trends

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

    quantities and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.57
     TAMBIÉN
    -0.52
     cereales
    -0.52
     Betrachtung
    -0.51
     Daß
    -0.50
    complexContent
    -0.50
     özellikle
    -0.50
     Gefühle
    -0.50
    baliknya
    -0.49
     Empfehlungen
    -0.49
    POSITIVE LOGITS
     dozens
    0.58
     hundreds
    0.54
     more
    0.53
     dozen
    0.52
     hundred
    0.52
    undred
    0.51
     additional
    0.49
     many
    0.48
     seventy
    0.46
     purpoſe
    0.46
    Act Density 0.066%

    No Known Activations