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

    Neuronpedia

    INDEX
    Explanations

    Acting roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     detection
    -0.07
     orb
    -0.07
     fighter
    -0.07
     CV
    -0.06
    'i
    -0.06
     parameters
    -0.06
     Aircraft
    -0.06
    esty
    -0.06
     XII
    -0.06
    ibrator
    -0.06
    POSITIVE LOGITS
     招
    0.07
    .pull
    0.06
    .productId
    0.06
    国产
    0.06
     Киє
    0.06
    ulpt
    0.06
    cret
    0.06
     xhttp
    0.06
     Creat
    0.06
     anyhow
    0.06
    Act Density 0.044%

    No Known Activations