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

    Neuronpedia

    INDEX
    Explanations

    age or time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .But
    -0.06
    슉
    -0.06
    =open
    -0.06
    .callbacks
    -0.06
     Sug
    -0.06
     brethren
    -0.06
    雁
    -0.06
    follower
    -0.06
    aight
    -0.06
    (hdr
    -0.06
    POSITIVE LOGITS
     downstairs
    0.08
     INTERNATIONAL
    0.08
    範
    0.07
    最小
    0.07
    أجر
    0.07
     החל
    0.07
    הפכו
    0.07
     __("
    0.07
     demean
    0.07
    <>(
    0.07
    Act Density 0.057%

    No Known Activations