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
     Webb
    -0.07
    ANGUAGE
    -0.06
    ¨
    -0.06
     frames
    -0.06
    Archivo
    -0.06
     attendees
    -0.06
     swinging
    -0.06
     semaphore
    -0.06
     hefty
    -0.06
    ber
    -0.06
    POSITIVE LOGITS
    /stdc
    0.07
    /|
    0.06
     easing
    0.06
    略
    0.06
    acak
    0.06
     discovered
    0.06
    บาท
    0.06
     ska
    0.06
     ukaz
    0.06
     wished
    0.06
    Act Density 0.013%

    No Known Activations