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

    Neuronpedia

    INDEX
    Explanations

    egg laid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vare
    0.41
     שלך
    0.41
     אשר
    0.41
    ótica
    0.41
    ot
    0.41
    Pennsylvania
    0.40
    さを
    0.40
     intoxicated
    0.40
     Confederacy
    0.40
     служ
    0.40
    POSITIVE LOGITS
     defList
    0.46
     trato
    0.43
     fave
    0.40
     eats
    0.39
     respald
    0.38
     exceeded
    0.38
     flaming
    0.38
     milhões
    0.38
    餬
    0.37
     leaks
    0.37
    Act Density 0.002%

    No Known Activations