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

    Neuronpedia

    INDEX
    Explanations

    occurrences of spatial or locational prepositions

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

    prepositions followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    berdayakan
    -0.66
     queſta
    -0.56
    KURZBESCHREIBUNG
    -0.55
    balleur
    -0.53
    出版年
    -0.53
    -0.53
    bayaran
    -0.53
     Monfieur
    -0.52
     ddelwed
    -0.52
     müſſen
    -0.51
    POSITIVE LOGITS
    makeText
    0.37
     finish
    0.33
     desk
    0.33
    InSection
    0.32
     Finishing
    0.32
    Parcelize
    0.31
     finishing
    0.31
     finished
    0.30
     initComponents
    0.30
     RM
    0.30
    Act Density 0.283%

    No Known Activations