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

    Neuronpedia

    INDEX
    Explanations

    scientific names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conversation
    -0.07
     mappings
    -0.07
    ardash
    -0.07
     liters
    -0.06
     Λ
    -0.06
    Wins
    -0.06
    ERAL
    -0.06
     goose
    -0.06
     longitud
    -0.06
    MimeType
    -0.06
    POSITIVE LOGITS
    ContextHolder
    0.06
     mos
    0.06
    .event
    0.06
     unnecessary
    0.06
    _SHARE
    0.06
    _Dec
    0.06
    .Point
    0.06
     shootout
    0.05
    tığını
    0.05
     freel
    0.05
    Act Density 0.029%

    No Known Activations