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

    Neuronpedia

    INDEX
    Explanations

    after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">$
    -0.29
    -eng
    -0.27
    è¿ĻæĿ¡
    -0.26
    анÑģ
    -0.25
    egan
    -0.25
    çĩİ
    -0.25
    ãģĤãĤĬãģ¾ãģĹãģŁ
    -0.25
    uarios
    -0.25
    OUSE
    -0.25
    ","\
    -0.24
    POSITIVE LOGITS
     art
    0.29
     fund
    0.28
    çĶ²
    0.27
     al
    0.26
     constraints
    0.25
    éļĶå£ģ
    0.25
    strict
    0.25
    æĬĬæīĭ
    0.25
     On
    0.24
     eas
    0.24
    Act Density 0.051%

    No Known Activations