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

    Neuronpedia

    INDEX
    Explanations

    listing tasks and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tay
    0.47
     Kansas
    0.47
     Iowa
    0.43
    都道府県
    0.42
    Taylor
    0.42
     Taylor
    0.42
     warranty
    0.41
    Tay
    0.41
    ఫీ
    0.40
     Step
    0.40
    POSITIVE LOGITS
     it
    0.46
    舟
    0.44
    छ
    0.43
     ĝi
    0.43
     enjo
    0.42
     escapar
    0.41
    ート
    0.40
    고자
    0.40
    શી
    0.39
    advice
    0.39
    Act Density 0.000%

    No Known Activations