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

    Neuronpedia

    INDEX
    Explanations

    Levels and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     মতে
    -0.08
     повідом
    -0.08
     narrowly
    -0.08
     прол
    -0.08
    ја
    -0.08
     Madaxweyne
    -0.08
     manaʻo
    -0.08
     njani
    -0.07
     করোন
    -0.07
     том
    -0.07
    POSITIVE LOGITS
    打造
    0.09
     boosts
    0.09
     boost
    0.09
     proficiency
    0.09
     attainable
    0.08
     mastery
    0.08
    wife
    0.08
    Boost
    0.08
    bonus
    0.08
    apper
    0.08
    Act Density 0.006%

    No Known Activations