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

    Neuronpedia

    INDEX
    Explanations

    general english text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    536
    -0.07
    ்
    -0.06
     которые
    -0.06
    vised
    -0.06
    moduleName
    -0.06
     pertinent
    -0.06
    processors
    -0.06
     ptr
    -0.06
    ые
    -0.06
    doc
    -0.06
    POSITIVE LOGITS
    وسی
    0.07
     Joey
    0.06
     Gonz
    0.06
     모집
    0.06
     juices
    0.06
    _cuda
    0.06
     всп
    0.06
     phishing
    0.06
    orney
    0.06
    Vent
    0.06
    Act Density 0.251%

    No Known Activations