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

    Neuronpedia

    INDEX
    Explanations

    connective phrases and conjunctions in sentences

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

    Mathematical equations or numerical patterns

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.50
    VIAF
    -0.41
    parsedMessage
    -0.40
    PerformLayout
    -0.40
     lisäksi
    -0.40
     TAMBÉM
    -0.38
    ंदीखरीदारी
    -0.37
    balleur
    -0.36
    Hund
    -0.36
    geslacht
    -0.36
    POSITIVE LOGITS
     CreateTagHelper
    0.64
     autorytatywna
    0.63
     незавершена
    0.49
    ⓧ
    0.48
     विश्वसनीयता
    0.48
    Élet
    0.48
    もと
    0.46
     Oka
    0.46
    __':
    0.45
    }{*}{
    0.44
    Act Density 0.014%

    No Known Activations