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

    Neuronpedia

    INDEX
    Explanations

    Habitats and ecology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Directions
    -0.07
    ス
    -0.07
    GER
    -0.06
    ize
    -0.06
    ,status
    -0.06
     PUT
    -0.06
    -points
    -0.06
    are
    -0.06
     Thus
    -0.06
    owania
    -0.06
    POSITIVE LOGITS
    0.08
     ";↵↵
    0.08
    ��
    0.07
    ✾
    0.07
    isory
    0.07
    _Map
    0.07
    �
    0.07
     Nicaragua
    0.06
    副教授
    0.06
    мол
    0.06
    Act Density 0.016%

    No Known Activations