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

    Neuronpedia

    INDEX
    Explanations

    Runtime

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PT
    -0.07
     describing
    -0.07
     MAP
    -0.07
    Carrier
    -0.07
    🤮
    -0.07
    different
    -0.07
     file
    -0.07
     Boo
    -0.07
    补
    -0.07
    “What
    -0.07
    POSITIVE LOGITS
     regimes
    0.07
    ヴァ
    0.07
     Lama
    0.07
     regimen
    0.07
     jedem
    0.06
    صاص
    0.06
     agendas
    0.06
    🍜
    0.06
     pobliżu
    0.06
     uống
    0.06
    Act Density 0.000%

    No Known Activations