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

    Neuronpedia

    INDEX
    Explanations

    finding facts or names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Eligibility
    0.47
    katapos
    0.47
    اؤ
    0.45
     Prothorax
    0.44
     Bedarf
    0.44
    щики
    0.44
     nejen
    0.44
     Daarom
    0.43
    enuh
    0.43
     সমাজের
    0.43
    POSITIVE LOGITS
     reim
    0.45
     lion
    0.44
     his
    0.43
     retract
    0.42
    rins
    0.41
     retardation
    0.40
     water
    0.40
     slide
    0.40
     sliding
    0.40
     drought
    0.40
    Act Density 0.002%

    No Known Activations