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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manuela
    -1.16
     Karla
    -1.15
     Kayla
    -1.14
     Hayley
    -1.11
     Mónica
    -1.05
     Valeria
    -1.03
     Rhonda
    -1.02
     Davide
    -1.02
     Maureen
    -1.01
     Marlene
    -1.00
    POSITIVE LOGITS
     who
    0.68
     Angele
    0.61
    ).—
    0.61
    Tetapi
    0.61
     Saver
    0.60
    urator
    0.60
     Mart
    0.60
    Filmographie
    0.60
    Quien
    0.60
     quien
    0.60
    Act Density 6.030%

    No Known Activations