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

    Neuronpedia

    INDEX
    Explanations

    vague words and phrases used in discussions of opinions, feelings, senses, and community and also finds references to official status

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rapid
    -0.32
    IMENTS
    -0.31
     distinct
    -0.30
    Vanjske
    -0.30
     unique
    -0.29
     constant
    -0.29
     terrain
    -0.28
     extra
    -0.28
     un
    -0.28
     basic
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.73
     myſelf
    0.71
     feroit
    0.71
    IndentedString
    0.71
    ArrowToggle
    0.70
    AsUp
    0.69
    Попис
    0.69
    Be
    0.68
     étoit
    0.67
     auroit
    0.67
    Act Density 38.748%

    No Known Activations