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

    Neuronpedia

    INDEX
    Explanations

    disabled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usion
    -0.08
    供销
    -0.07
     accordance
    -0.07
    Bron
    -0.07
     Pon
    -0.07
    ▨
    -0.07
    装配
    -0.07
    〔
    -0.07
    唯
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     documentation
    0.07
    Tue
    0.07
     נחשב
    0.07
    化肥
    0.07
    .containsKey
    0.07
     ASCII
    0.07
    ismet
    0.06
     swearing
    0.06
    ,axis
    0.06
    읜
    0.06
    Act Density 0.009%

    No Known Activations