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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roberto
    -0.07
     PCR
    -0.06
     arthritis
    -0.06
     sampled
    -0.06
     expose
    -0.06
     پزشکی
    -0.06
     Helen
    -0.06
    -desc
    -0.06
     LV
    -0.06
    >).
    -0.06
    POSITIVE LOGITS
     ذات
    0.06
    	constexpr
    0.06
    ง
    0.06
    Lt
    0.06
     PROCESS
    0.06
    typeparam
    0.06
    AT
    0.06
     Bahamas
    0.06
    kept
    0.06
     scripting
    0.06
    Act Density 0.012%

    No Known Activations