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

    Neuronpedia

    INDEX
    Explanations

    Code licensing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maxi
    -0.07
    삮
    -0.07
    钦
    -0.07
     nhu
    -0.06
     Пре
    -0.06
     Grupo
    -0.06
    <nav
    -0.06
     Ad
    -0.06
     Darwin
    -0.06
     kInstruction
    -0.06
    POSITIVE LOGITS
     Atmospheric
    0.08
    (Program
    0.07
    tryside
    0.07
    臟
    0.07
    ossible
    0.07
    되었다
    0.07
    (local
    0.07
    府
    0.07
    reachable
    0.07
    _individual
    0.07
    Act Density 0.000%

    No Known Activations