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

    Neuronpedia

    INDEX
    Explanations

    considering options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ऑफ
    -0.07
    TN
    -0.07
     Aussie
    -0.07
     одну
    -0.06
    ONES
    -0.06
    DVD
    -0.06
    DES
    -0.06
     Herbert
    -0.06
    问题
    -0.06
    Hyper
    -0.06
    POSITIVE LOGITS
     stained
    0.07
    []
    0.07
     ground
    0.07
    .RichTextBox
    0.06
     Кат
    0.06
    ोप
    0.06
     just
    0.06
     stain
    0.06
     saves
    0.06
     dank
    0.06
    Act Density 0.062%

    No Known Activations