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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بغداد
    -0.07
    丰胸
    -0.07
    _SYMBOL
    -0.06
     ny
    -0.06
     Deutschland
    -0.06
    睫毛
    -0.06
     руков
    -0.06
    �
    -0.06
     Spain
    -0.06
     conserve
    -0.06
    POSITIVE LOGITS
    אבא
    0.07
     Scores
    0.07
     crews
    0.07
     confronted
    0.07
    ının
    0.07
     grounded
    0.07
    选项
    0.07
    多种
    0.07
    لاء
    0.06
    ומר
    0.06
    Act Density 0.023%

    No Known Activations