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

    Neuronpedia

    INDEX
    Explanations

    [blank] ]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    fal
    -0.10
    arih
    -0.10
    anco
    -0.09
    OnChange
    -0.09
    kok
    -0.09
    ãĢĢi
    -0.09
     ëĦ¤ìĿ´íĬ¸
    -0.08
    ifr
    -0.08
    acha
    -0.08
    599
    -0.08
    POSITIVE LOGITS
    ://
    0.09
    sis
    0.09
     Aires
    0.09
    eldo
    0.09
     necess
    0.09
    heimer
    0.08
    HING
    0.08
     inclined
    0.08
    _NR
    0.08
     Fill
    0.08
    Act Density 0.234%

    No Known Activations