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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ex
    -0.07
    ML
    -0.07
    ठ
    -0.06
     Sky
    -0.06
     waste
    -0.06
    INFRINGEMENT
    -0.06
     Freud
    -0.06
     Thumb
    -0.06
     Level
    -0.06
    肖
    -0.06
    POSITIVE LOGITS
    [code
    0.07
     contentious
    0.07
    igInteger
    0.06
    HomeAsUpEnabled
    0.06
    illance
    0.06
    _syn
    0.06
    QUEUE
    0.06
     restricting
    0.06
    едера
    0.06
    -reply
    0.06
    Act Density 0.002%

    No Known Activations