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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assumptions or predictions

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

    precisely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.62
    Diweddarwch
    -0.57
     صوتيه
    -0.57
    IContainer
    -0.52
     nahilalakip
    -0.50
    orithm
    -0.47
    cery
    -0.44
    égias
    -0.44
     चीज़ों
    -0.43
     considérons
    -0.43
    POSITIVE LOGITS
    featureID
    0.45
     justamente
    0.39
     ioutil
    0.36
    GTCX
    0.35
    penup
    0.35
     المعيارى
    0.34
    MetaObject
    0.33
     hObject
    0.33
     właśnie
    0.33
     precisamente
    0.33
    Act Density 0.031%

    No Known Activations