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

    Neuronpedia

    INDEX
    Explanations

    alternating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wisdom
    -0.08
     Anch
    -0.08
    anch
    -0.08
     accountable
    -0.08
    aways
    -0.08
     what
    -0.07
     Ish
    -0.07
     PREMI
    -0.07
     Seven
    -0.07
     Prem
    -0.07
    POSITIVE LOGITS
     fluctu
    0.11
    变化
    0.11
     repeating
    0.11
     periodically
    0.10
     repetition
    0.09
     changing
    0.09
    周期
    0.09
    Changing
    0.09
     fluctuate
    0.09
     تغير
    0.09
    Act Density 0.006%

    No Known Activations