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

    Neuronpedia

    INDEX
    Explanations

    code/markup snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "And
    -0.09
     Within
    -0.07
    pcs
    -0.07
    🐨
    -0.06
     الموقع
    -0.06
     "/
    -0.06
    ("/")↵
    -0.06
    훜
    -0.06
     maternal
    -0.06
     lush
    -0.06
    POSITIVE LOGITS
     Emit
    0.08
    iction
    0.07
     Pocket
    0.07
    EXP
    0.07
     blame
    0.07
     uns
    0.07
     exhilar
    0.06
     baptism
    0.06
    𪨰
    0.06
    电动
    0.06
    Act Density 0.051%

    No Known Activations