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

    Neuronpedia

    INDEX
    Explanations

    code blocks ending with `#`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Subsequent
    0.47
    া
    0.46
    itive
    0.46
    a
    0.45
    আর
    0.45
    itively
    0.45
     Wszyst
    0.43
    nul
    0.43
    ibility
    0.43
    forbidden
    0.42
    POSITIVE LOGITS
    د
    0.55
    ר
    0.51
    𝘶
    0.51
     scra
    0.50
    𝘱
    0.50
    ب
    0.50
    𝘴
    0.50
    ORIAL
    0.49
    serrat
    0.48
     gestalten
    0.48
    Act Density 0.014%

    No Known Activations