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

    Neuronpedia

    INDEX
    Explanations

    actions related to taking or handling items

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    verb + particle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.34
     of
    -0.33
     at
    -0.31
     Freund
    -0.31
     the
    -0.29
     by
    -0.29
     至
    -0.28
     as
    -0.28
    Source
    -0.28
    ,
    -0.27
    POSITIVE LOGITS
     queſta
    0.93
    majánló
    0.93
     Geiſt
    0.91
     ſeine
    0.90
     '\\;'
    0.90
     Weiſe
    0.88
    expandindo
    0.88
    <unused3>
    0.87
    <pad>
    0.86
    <unused17>
    0.86
    Act Density 0.507%

    No Known Activations