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

    Neuronpedia

    INDEX
    Explanations

    multiple solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ozilla
    -0.09
    elang
    -0.08
     guk
    -0.08
    屁股
    -0.07
     bele
    -0.07
    ffic
    -0.07
     voluptas
    -0.07
     evenings
    -0.07
    _Enable
    -0.07
    passed
    -0.07
    POSITIVE LOGITS
     ambiguous
    0.11
     Choose
    0.09
     cautious
    0.09
     ambiguity
    0.09
     definitive
    0.08
     ±
    0.08
     deterministic
    0.08
     definite
    0.08
     rä
    0.08
     choose
    0.08
    Act Density 0.071%

    No Known Activations