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

    Neuronpedia

    INDEX
    Explanations

    Wars

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Couple
    -0.07
    issors
    -0.06
    пня
    -0.06
    .Objects
    -0.06
    市場
    -0.06
     кле
    -0.06
    sh
    -0.06
    .drawLine
    -0.06
     Cy
    -0.06
     bamboo
    -0.06
    POSITIVE LOGITS
     UNIT
    0.07
    (priv
    0.07
     Pokémon
    0.07
    Louis
    0.06
     Wars
    0.06
     entertainment
    0.06
     Poss
    0.06
    Upon
    0.06
     pert
    0.06
    　 　 　 　 　 　
    0.06
    Act Density 0.014%

    No Known Activations