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

    Neuronpedia

    INDEX
    Explanations

    technology and business

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ˆ
    -0.07
    ét
    -0.06
    impact
    -0.06
    stim
    -0.06
    ‹
    -0.06
    DON
    -0.06
    elig
    -0.06
    achi
    -0.06
    (handle
    -0.06
    -case
    -0.06
    POSITIVE LOGITS
    軟
    0.07
    )){↵↵
    0.06
    arial
    0.06
    _EXTERN
    0.06
     آز
    0.06
     Raqqa
    0.06
     Midlands
    0.06
    erable
    0.06
    ++){
↵
    0.06
    atisf
    0.06
    Act Density 0.108%

    No Known Activations