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

    Neuronpedia

    INDEX
    Explanations

    chemical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("~/
    -0.09
    malloc
    -0.08
    ================================================================================
    -0.07
    忘
    -0.07
     TOOL
    -0.07
     Develop
    -0.07
    PASSWORD
    -0.07
     większo
    -0.07
    xFA
    -0.07
    产业集聚
    -0.06
    POSITIVE LOGITS
     müşteri
    0.07
     sleep
    0.07
     Kiev
    0.07
    ологии
    0.07
     çıkış
    0.07
    pillar
    0.07
     Ridley
    0.06
     öğrenci
    0.06
    "}
    0.06
    _cos
    0.06
    Act Density 0.053%

    No Known Activations