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

    Neuronpedia

    INDEX
    Explanations

    reactive/argumentative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Org
    -0.07
    itant
    -0.07
     respondents
    -0.07
    aight
    -0.07
     september
    -0.07
    ド
    -0.07
     губ
    -0.07
    ille
    -0.07
     developmental
    -0.06
    POSITIVE LOGITS
     �
    0.07
     칼
    0.07
     Раз
    0.06
    0.06
     peas
    0.06
    .zone
    0.05
     اعتماد
    0.05
     pena
    0.05
     гра
    0.05
    _Application
    0.05
    Act Density 0.425%

    No Known Activations