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

    Neuronpedia

    INDEX
    Explanations

    hips

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <number
    -0.08
    -trigger
    -0.07
    的理念
    -0.07
    ניוזלטר
    -0.07
     الإثن
    -0.07
    ㄴ
    -0.07
    .DATE
    -0.07
    digital
    -0.07
     gaming
    -0.07
     Throwable
    -0.07
    POSITIVE LOGITS
     sä
    0.07
     professional
    0.07
    拿出来
    0.07
    バラ
    0.07
     faithfully
    0.07
     insured
    0.06
     intact
    0.06
     recyclerView
    0.06
    ']]
    0.06
    öße
    0.06
    Act Density 0.007%

    No Known Activations