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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences indicating provenance or origin

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

    made from

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ändå
    -0.58
     normalidad
    -0.54
    batore
    -0.54
    ública
    -0.54
     चीज़ों
    -0.50
     tendência
    -0.49
    ⓧ
    -0.49
     sebagainya
    -0.48
    WithIOException
    -0.48
     satisfacción
    -0.48
    POSITIVE LOGITS
    .*")]
    0.43
     reusable
    0.40
    躇
    0.39
     Vainqueur
    0.39
    ')}}">
    0.38
     dry
    0.37
    )))));
    0.37
     Jesu
    0.36
     utilizzando
    0.36
     utilizing
    0.36
    Act Density 0.011%

    No Known Activations