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

    Neuronpedia

    INDEX
    Explanations

    passion and drive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ่
    2.05
    us
    1.98
    ির
    1.80
    т
    1.74
    ้
    1.72
    í
    1.66
    bbene
    1.64
    ிட்ட
    1.60
    iness
    1.59
    ons
    1.52
    POSITIVE LOGITS
    ﺹ
    2.08
     dearly
    1.98
    데
    1.88
    ﻭ
    1.64
    p
    1.54
    謳
    1.54
    벗
    1.52
     snugly
    1.51
    澎
    1.51
    да
    1.50
    Act Density 0.005%

    No Known Activations