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

    Neuronpedia

    INDEX
    Explanations

    Bg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MA
    -0.08
    峪
    -0.07
    哭
    -0.07
    Document
    -0.07
    不懂
    -0.07
     وأ
    -0.07
     Suarez
    -0.07
    르
    -0.07
    CreatedAt
    -0.07
     ok
    -0.06
    POSITIVE LOGITS
    antasy
    0.08
    /Instruction
    0.07
    ❎
    0.07
    _anchor
    0.07
     פרסום
    0.06
     המשחק
    0.06
    .want
    0.06
    (il
    0.06
    (mod
    0.06
     Behind
    0.06
    Act Density 0.002%

    No Known Activations