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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ترین
    -0.06
     三
    -0.06
    ServletRequest
    -0.06
     lantern
    -0.06
     Gulf
    -0.06
     /><
    -0.06
    PASS
    -0.06
     ("<
    -0.06
     छ
    -0.06
     aktivit
    -0.06
    POSITIVE LOGITS
    їна
    0.06
     bilingual
    0.06
    839
    0.06
    ».
    0.06
    -list
    0.06
    Karen
    0.06
    합
    0.06
    NumberOf
    0.06
    Checkout
    0.06
    jících
    0.06
    Act Density 0.000%

    No Known Activations