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

    Neuronpedia

    INDEX
    Explanations

    listing and enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kulture
    1.07
     penyakit
    0.97
     demokrasi
    0.97
     당신
    0.97
     malnutrition
    0.94
     communism
    0.93
     feminism
    0.92
     homelessness
    0.92
    グッズ
    0.91
     بیماری
    0.91
    POSITIVE LOGITS
     notable
    0.95
    Notable
    0.93
     notably
    0.92
    Several
    0.90
    Numerous
    0.89
    Preliminary
    0.88
     notables
    0.87
    several
    0.84
    Notably
    0.83
     Notable
    0.82
    Act Density 0.063%

    No Known Activations