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

    Neuronpedia

    INDEX
    Explanations

    instructions for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rigging
    0.39
     pesawat
    0.38
    ähl
    0.38
    ائص
    0.37
    skine
    0.36
    एस
    0.36
     preh
    0.36
    ärer
    0.36
     ближе
    0.35
    anjutkan
    0.35
    POSITIVE LOGITS
    Dining
    0.38
     York
    0.38
    expédition
    0.37
    Instit
    0.37
    誹
    0.37
    やり
    0.36
    ჯგუფი
    0.36
    🍽
    0.36
     `=`,
    0.36
     түр
    0.35
    Act Density 0.000%

    No Known Activations