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

    Neuronpedia

    INDEX
    Explanations

    scientific elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    τό
    -0.07
     diver
    -0.07
    htar
    -0.06
    ジ
    -0.06
     เ�
    -0.06
    (Time
    -0.06
    첨부
    -0.06
    цию
    -0.06
    施
    -0.06
     flood
    -0.06
    POSITIVE LOGITS
    ует
    0.08
     Swagger
    0.07
     člověk
    0.07
    NoArgsConstructor
    0.06
     deserving
    0.06
    очный
    0.06
    #g
    0.06
     Caroline
    0.06
     zastav
    0.06
    +'"
    0.06
    Act Density 0.020%

    No Known Activations