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

    Neuronpedia

    INDEX
    Explanations

    customer testimonials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     شع
    -0.08
    输
    -0.07
     Joined
    -0.07
     Пар
    -0.07
    十六
    -0.07
     nostro
    -0.06
    	col
    -0.06
     열
    -0.06
    (FALSE
    -0.06
    不可
    -0.06
    POSITIVE LOGITS
     */↵↵↵
    0.06
     afirm
    0.06
     Loki
    0.06
    <footer
    0.06
     capitalize
    0.06
     gig
    0.06
     prezident
    0.05
    他
    0.05
     nymph
    0.05
     totiž
    0.05
    Act Density 0.071%

    No Known Activations