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

    Neuronpedia

    INDEX
    Explanations

    Same titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _die
    -0.08
    嫩
    -0.08
     तरी
    -0.08
     blocked
    -0.08
    <Response
    -0.07
    -counter
    -0.07
     redact
    -0.07
    _trait
    -0.07
     counters
    -0.07
    Counters
    -0.07
    POSITIVE LOGITS
    -même
    0.08
     പേര
    0.08
     stesso
    0.08
     yakni
    0.08
    miştir
    0.08
     aptly
    0.08
     фир
    0.07
     literally
    0.07
    属
    0.07
     নামে
    0.07
    Act Density 0.011%

    No Known Activations