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

    Neuronpedia

    INDEX
    Explanations

    appearances of the words "it", "not", "she", "he", "that", "your", and "possible"

    oai_token-act-pair · gemini-2.0-flash

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.02
    ISupport
    -0.92
    enumii
    -0.80
     חיצוניים
    -0.80
    Portale
    -0.79
    __*/
    -0.77
    !*\
    -0.76
    %?
    -0.75
    forRoot
    -0.74
    Portail
    -0.71
    POSITIVE LOGITS
    Exception
    0.43
    us
    0.43
    toMap
    0.40
     familiare
    0.39
     soeur
    0.39
     bancaire
    0.38
    ран
    0.37
     vocale
    0.37
     fortemente
    0.37
     especializados
    0.36
    Act Density 3.751%

    No Known Activations