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

    Neuronpedia

    INDEX
    Explanations

    the word "user" and words and abbreviations closely associated with it

    oai_token-act-pair · gemini-2.0-flash

    user

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Portale
    -1.03
     consultato
    -1.00
     <<<<<<<<<<<<<<
    -0.89
     Anſ
    -0.88
     Wiktionnaire
    -0.88
    ſelf
    -0.85
     transfieras
    -0.84
    ſelves
    -0.83
    ModelSerializer
    -0.82
    ècie
    -0.81
    POSITIVE LOGITS
    land
    0.47
    міна
    0.45
    бро
    0.44
    an
    0.44
    <eos>
    0.41
     stat
    0.40
     rú
    0.40
    мина
    0.40
    stat
    0.39
    com
    0.39
    Act Density 0.665%

    No Known Activations