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

    Neuronpedia

    INDEX
    Explanations

    concepts followed by definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nač
    0.37
    ்க்கு
    0.37
    ਗਾ
    0.36
    ঁর
    0.36
    čet
    0.35
    ronaut
    0.35
    phpunit
    0.34
     garantire
    0.34
    udad
    0.34
    azia
    0.34
    POSITIVE LOGITS
     وكذلك
    0.44
     predominate
    0.43
     consid
    0.38
     likewise
    0.36
     sekä
    0.36
     également
    0.36
     aspects
    0.36
     aspetti
    0.35
     aswell
    0.35
     interna
    0.35
    Act Density 0.089%

    No Known Activations