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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beliefs
    -0.07
     konuştu
    -0.07
    _exact
    -0.06
    Essay
    -0.06
    theorem
    -0.06
    ुमत
    -0.06
    ematic
    -0.06
     kontakt
    -0.06
    ности
    -0.06
     transitions
    -0.06
    POSITIVE LOGITS
     Very
    0.07
     expended
    0.06
     Heal
    0.06
     shorthand
    0.06
     Received
    0.06
     Santa
    0.06
     Spartan
    0.06
    PARATOR
    0.06
     XMLHttpRequest
    0.06
    _https
    0.06
    Act Density 0.002%

    No Known Activations