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

    Neuronpedia

    INDEX
    Explanations

    new

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🛒
    -0.07
     resurrect
    -0.07
     fx
    -0.07
     annex
    -0.07
     Claw
    -0.07
    تان
    -0.06
     wah
    -0.06
     langu
    -0.06
    陌
    -0.06
     מתחת
    -0.06
    POSITIVE LOGITS
     observation
    0.07
     self
    0.07
    事
    0.07
    "B
    0.07
    tests
    0.07
    vidia
    0.07
    "D
    0.07
     Correspond
    0.07
    环境保护
    0.06
    情況
    0.06
    Act Density 0.012%

    No Known Activations