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

    Neuronpedia

    INDEX
    Explanations

    uppercase letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    森
    -0.26
    ling
    -0.26
    ä¹³
    -0.26
     Erect
    -0.25
    OfClass
    -0.25
    AAF
    -0.24
    jin
    -0.24
    çıº
    -0.24
    )'),↵
    -0.24
    /topic
    -0.24
    POSITIVE LOGITS
    åıijå±ķä¸Ń
    0.30
    éĩİå¿ĥ
    0.28
     frag
    0.27
    躺
    0.26
    åİĭåĬĽ
    0.25
     paren
    0.25
    fffffff
    0.25
    çİĭåĽ½
    0.25
    çļĦåİĭåĬĽ
    0.24
    躺çĿĢ
    0.24
    Act Density 0.479%

    No Known Activations