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

    Neuronpedia

    INDEX
    Explanations

    ::

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    JP
    -0.07
    gia
    -0.07
    [P
    -0.07
     Led
    -0.06
    iasi
    -0.06
     ValidationResult
    -0.06
    ASI
    -0.06
    看看
    -0.06
    слід
    -0.06
    _configuration
    -0.06
    POSITIVE LOGITS
     požad
    0.07
    .song
    0.06
    _AUTHOR
    0.06
     گروه
    0.06
    Dick
    0.06
    .rank
    0.06
     Rus
    0.06
     dunk
    0.06
     이를
    0.06
    testdata
    0.06
    Act Density 0.005%

    No Known Activations