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

    Neuronpedia

    INDEX
    Explanations

    offer to create

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Because
    0.34
     can
    0.30
     Assuming
    0.30
     pursuant
    0.30
     Since
    0.29
    recogn
    0.29
     bertujuan
    0.28
     beginnen
    0.28
     balloon
    0.28
     首先
    0.28
    POSITIVE LOGITS
     mengubah
    0.39
     Umsetzung
    0.39
    ющими
    0.34
     potre
    0.34
     numquam
    0.34
    ຄ້າ
    0.34
     overstated
    0.34
    کي
    0.34
     conteúdos
    0.34
    മ്പോ
    0.33
    Act Density 0.147%

    No Known Activations