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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Station
    -0.07
    .SizeF
    -0.07
     Nimbus
    -0.07
    (py
    -0.06
    周年
    -0.06
    izont
    -0.06
    (fmt
    -0.06
     yön
    -0.06
     tc
    -0.06
     زی
    -0.06
    POSITIVE LOGITS
    -DD
    0.07
    才能
    0.06
    тобы
    0.06
    업체
    0.06
    Couldn
    0.06
    لود
    0.06
     lawyers
    0.06
     abused
    0.06
     ولكن
    0.06
    нимает
    0.06
    Act Density 0.009%

    No Known Activations