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

    Neuronpedia

    INDEX
    Explanations

    code and programming errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     쇼
    -0.06
    ARB
    -0.06
     heartfelt
    -0.06
     hmac
    -0.06
     immense
    -0.06
    erse
    -0.06
    aro
    -0.06
     eco
    -0.06
     arc
    -0.06
     agricultural
    -0.06
    POSITIVE LOGITS
     Yeni
    0.07
    locked
    0.07
     ル
    0.07
     �
    0.07
     Snape
    0.07
    pliers
    0.06
    met
    0.06
     SUBSTITUTE
    0.06
     did
    0.06
     الز
    0.06
    Act Density 0.050%

    No Known Activations