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

    Neuronpedia

    INDEX
    Explanations

    programming languages and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ཋ
    0.47
    kében
    0.41
    uillez
    0.39
    TING
    0.38
    ק
    0.38
    ata
    0.38
    𝘬
    0.38
    ise
    0.37
    וד
    0.37
    ANGE
    0.37
    POSITIVE LOGITS
     و
    0.36
    ؛
    0.35
     (
    0.33
     orchards
    0.33
    ،
    0.33
     primavera
    0.32
     bonnes
    0.32
     meski
    0.32
     ancak
    0.31
     estat
    0.31
    Act Density 0.075%

    No Known Activations