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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     View
    -0.07
     orthogonal
    -0.06
    206
    -0.06
    _season
    -0.06
    Category
    -0.06
    Scale
    -0.06
     ICT
    -0.06
     Avenue
    -0.06
     towns
    -0.06
     bombing
    -0.06
    POSITIVE LOGITS
    [ch
    0.08
     нагруз
    0.07
     분
    0.07
     مشخص
    0.07
    �
    0.07
    elleicht
    0.07
     дослід
    0.07
    овано
    0.07
    乳
    0.06
    晶
    0.06
    Act Density 0.012%

    No Known Activations