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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    却
    -0.09
     емес
    -0.09
     nincs
    -0.08
    Fuck
    -0.08
     보여
    -0.08
    ']?>"
    -0.08
     juist
    -0.08
     બની
    -0.08
    不到
    -0.08
     hence
    -0.08
    POSITIVE LOGITS
     disclaim
    0.09
     rationale
    0.09
     exemplos
    0.08
     ejemplos
    0.08
     उदाहरण
    0.08
     tailored
    0.08
     explanations
    0.07
     thoughtfully
    0.07
     timeline
    0.07
     examples
    0.07
    Act Density 0.036%

    No Known Activations