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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Participant
    -0.06
     �
    -0.06
     contestant
    -0.06
     caratter
    -0.06
    ibraltar
    -0.06
    صة
    -0.06
     Pike
    -0.06
    .UndefOr
    -0.06
     swarm
    -0.06
    rad
    -0.06
    POSITIVE LOGITS
    жение
    0.06
     adequate
    0.06
    ↵                    ↵
    0.06
     greeting
    0.06
     clim
    0.06
    anean
    0.06
     capitalize
    0.06
    Black
    0.06
    quisar
    0.06
    اران
    0.06
    Act Density 0.039%

    No Known Activations