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

    Neuronpedia

    INDEX
    Explanations

    linked

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    allee
    -0.27
    å¿Ĺ
    -0.27
    oulouse
    -0.26
     fist
    -0.26
     knowledge
    -0.26
     breath
    -0.26
    çŁ¥è¯ĨçĤ¹
    -0.25
    ष
    -0.25
    Stars
    -0.25
    OURS
    -0.25
    POSITIVE LOGITS
    åŃĺæĶ¾
    0.26
    stad
    0.25
    çļĦ人æĿ¥è¯´
    0.25
    ä»Ģä¹Īäºĭ
    0.25
    è¿ĩé«ĺ
    0.25
    çݩ家æĿ¥è¯´
    0.25
    éħ°
    0.24
    jad
    0.24
    development
    0.24
     pry
    0.24
    Act Density 0.287%

    No Known Activations