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

    Neuronpedia

    INDEX
    Explanations

    supersets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solace
    -0.09
     miljo
    -0.08
     madd
    -0.08
    (evt
    -0.08
    Lessons
    -0.08
     Sho
    -0.08
     millioner
    -0.08
    DAR
    -0.08
     Hiroshima
    -0.08
     муд
    -0.08
    POSITIVE LOGITS
     alternating
    0.09
     staggering
    0.08
     तुरंत
    0.08
     stagger
    0.08
    גיע
    0.08
     Bari
    0.08
    quences
    0.08
     consecutive
    0.08
     Altern
    0.08
     consecut
    0.08
    Act Density 0.007%

    No Known Activations