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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leafs
    -0.09
     يص
    -0.07
    (Clone
    -0.07
     توقع
    -0.07
    łoż
    -0.07
     Heated
    -0.07
     Tango
    -0.07
     magically
    -0.07
    weging
    -0.07
     traz
    -0.07
    POSITIVE LOGITS
    <|endoftext|>
    0.08
     denn
    0.08
    .ad
    0.08
    0.08
     sein
    0.07
     vera
    0.07
    .text
    0.07
     društ
    0.07
     spelled
    0.07
    <|reserved_200016|>
    0.07
    Act Density 1.247%
    No Known Activations