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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tbilisi
    0.46
    Pascal
    0.43
    ቬ
    0.43
     Barcelona
    0.41
     Pascal
    0.40
     paralle
    0.40
     Istanbul
    0.40
    蝮
    0.39
    descriptions
    0.38
     descriptions
    0.38
    POSITIVE LOGITS
     pronouns
    0.95
     pronoun
    0.87
    pron
    0.59
    Pron
    0.59
     Pron
    0.56
     word
    0.51
     words
    0.51
     demonstr
    0.51
    WORDS
    0.51
    Words
    0.50
    Act Density 0.070%

    No Known Activations