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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to measurements and specifications

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

    prisoners of war

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    antaranya
    -0.52
    󠁣
    -0.40
     mấy
    -0.37
     abroad
    -0.36
    real
    -0.35
    bigger
    -0.35
     noqa
    -0.34
     uploading
    -0.34
    st
    -0.34
     Gems
    -0.33
    POSITIVE LOGITS
    fromnode
    0.71
    Rujuakan
    0.58
    исленность
    0.58
     faſt
    0.56
     informée
    0.56
     Савезне
    0.54
     agrí
    0.51
    锈钢
    0.50
     Réponses
    0.48
    iſh
    0.48
    Act Density 0.126%

    No Known Activations