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

    Neuronpedia

    INDEX
    Explanations

    resistance based

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualifying
    0.38
    rolling
    0.38
    Charset
    0.38
     ઘટ
    0.37
     disregarded
    0.37
     ದು
    0.37
     માંગ
    0.37
    дня
    0.36
     empez
    0.35
     flaming
    0.34
    POSITIVE LOGITS
    iniert
    0.37
    Developed
    0.37
     khảo
    0.37
    Cold
    0.37
    اق
    0.36
    Related
    0.35
    تع
    0.35
     भौ
    0.35
     Industrial
    0.34
    馆
    0.34
    Act Density 0.000%

    No Known Activations