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

    Neuronpedia

    INDEX
    Explanations

    web content/forum discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())
↵
↵
    -0.07
    @GeneratedValue
    -0.07
    工程技术
    -0.06
    違い
    -0.06
     attracts
    -0.06
     }*/↵
    -0.06
    _tau
    -0.06
     tells
    -0.06
     dissent
    -0.06
     amet
    -0.06
    POSITIVE LOGITS
     Gum
    0.08
    COPE
    0.07
    เกร
    0.07
    IDES
    0.07
    zure
    0.07
    рог
    0.07
     Hyderabad
    0.07
    㙦
    0.07
    ﰴ
    0.06
    веден
    0.06
    Act Density 0.058%

    No Known Activations