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

    Neuronpedia

    INDEX
    Explanations

    Originally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     米
    -0.07
    retched
    -0.07
     tud
    -0.07
    }'",
    -0.07
     ogs
    -0.06
    .metrics
    -0.06
    _os
    -0.06
     predecess
    -0.06
     abrupt
    -0.06
    Dry
    -0.06
    POSITIVE LOGITS
     Surround
    0.06
     cater
    0.06
     Cathy
    0.06
     приб
    0.06
     февраля
    0.06
    {name
    0.06
    ipel
    0.06
     objections
    0.06
     Leia
    0.06
     Vega
    0.06
    Act Density 0.009%

    No Known Activations