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

    Neuronpedia

    INDEX
    Explanations

    _MAP or _TABLE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .ms
    -0.07
    ﯛ
    -0.07
    antz
    -0.07
    ünk
    -0.07
    (admin
    -0.07
     gest
    -0.07
     guests
    -0.07
    Ѩ
    -0.07
     Meng
    -0.07
    .size
    -0.06
    POSITIVE LOGITS
    红色
    0.09
    _MODE
    0.07
    LM
    0.07
    时时彩
    0.07
    떵
    0.07
    推出的
    0.07
    Overlay
    0.07
     excluding
    0.07
    HB
    0.07
    .assertThat
    0.06
    Act Density 0.000%

    No Known Activations