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

    Neuronpedia

    INDEX
    Explanations

    mathematical and code expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     convulsions
    0.38
     dusting
    0.38
     idée
    0.37
     engravings
    0.37
     solitons
    0.37
     coverings
    0.37
     tongs
    0.36
     electrolysis
    0.36
     angling
    0.36
     indicaciones
    0.36
    POSITIVE LOGITS
    >$
    0.55
    >
    0.38
    >${
    0.36
    d
    0.35
    中国
    0.34
    ﺩ
    0.33
    з
    0.32
    Design
    0.32
    눈
    0.32
    に戻
    0.31
    Act Density 0.000%

    No Known Activations