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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kind
    -0.07
     математи
    -0.07
    ி
    -0.06
     perfected
    -0.06
     меньше
    -0.06
    aned
    -0.06
     seminal
    -0.06
    hay
    -0.06
     unavailable
    -0.06
     tarif
    -0.06
    POSITIVE LOGITS
    _Entity
    0.07
     Patreon
    0.06
     كرد
    0.06
    DataContext
    0.06
    仍
    0.06
     OTA
    0.06
    出售
    0.06
     blankets
    0.06
     собой
    0.06
    .Connection
    0.06
    Act Density 0.002%

    No Known Activations