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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ayah
    -0.28
    央
    -0.27
    è¿ĩçļĦ
    -0.26
    aya
    -0.26
    ioctl
    -0.26
    ãĥijãĤ¤
    -0.25
    åĽłç´ł
    -0.25
    jay
    -0.24
     disap
    -0.24
    æ·®åįĹ
    -0.24
    POSITIVE LOGITS
    ARS
    0.28
     <![
    0.27
     Sho
    0.26
    èĨ³
    0.25
    ä»ĸ认为
    0.24
     relay
    0.24
    rell
    0.24
    caps
    0.24
    ä»ĸçļĦ
    0.24
    ars
    0.23
    Act Density 0.017%

    No Known Activations