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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ^K
    -0.34
    коÑģ
    -0.28
    ç¨ĭ
    -0.27
    dT
    -0.26
     vistas
    -0.26
    osit
    -0.25
    æķĻ
    -0.24
     Heal
    -0.24
    æĸ¹åľĨ
    -0.24
    TAIL
    -0.23
    POSITIVE LOGITS
     promising
    0.33
    hoff
    0.30
    æĹłçĸij
    0.29
     straightforward
    0.29
     parece
    0.28
    remium
    0.28
    åŃ°
    0.28
     futuro
    0.27
    çļĦ好
    0.27
    emoth
    0.27
    Act Density 0.013%

    No Known Activations