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

    Neuronpedia

    INDEX
    Explanations

    names of companies or people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     أيضاً
    0.47
    Ᏼ
    0.46
     Также
    0.42
     belang
    0.42
     erfolgt
    0.41
     letzt
    0.41
     fluke
    0.41
     frans
    0.41
     definito
    0.40
     beginnen
    0.40
    POSITIVE LOGITS
    юро
    0.40
    username
    0.38
    အရေ
    0.37
    驕
    0.36
    tweets
    0.35
    isDirectory
    0.35
     Tianjin
    0.35
     Announced
    0.34
    navbar
    0.34
    /@
    0.34
    Act Density 0.012%

    No Known Activations