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

    Neuronpedia

    INDEX
    Explanations

    names of individuals associated with storytelling or artistic endeavors

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

    Followed by past tense verbs

    np_acts-logits-general · gemini-2.0-flash

    names followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dolayı
    -0.38
    ".
    -0.35
     parem
    -0.35
     }.
    -0.33
     arba
    -0.33
    ouret
    -0.32
    }.
    -0.32
    [].
    -0.31
    jší
    -0.31
     adet
    -0.31
    POSITIVE LOGITS
     has
    1.41
     was
    1.28
     also
    1.17
     had
    1.14
     took
    1.10
     hasn
    1.07
     is
    1.01
     heeft
    1.01
     telah
    0.99
     said
    0.98
    Act Density 0.829%

    No Known Activations