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

    Neuronpedia

    INDEX
    Explanations

    Time and scheduling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [++
    -0.08
     statist
    -0.08
     langleb
    -0.07
     un
    -0.07
    agh
    -0.07
    (++
    -0.07
     selles
    -0.07
     implemented
    -0.07
    �
    -0.07
    (Thread
    -0.07
    POSITIVE LOGITS
    提前
    0.16
    小时前
    0.14
     заранее
    0.13
     antecip
    0.12
     לפני
    0.12
     anticipating
    0.11
    分钟前
    0.11
     anticip
    0.11
     πριν
    0.11
     beforehand
    0.11
    Act Density 0.026%

    No Known Activations