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

    Neuronpedia

    INDEX
    Explanations

    Spreadsheet code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tallest
    -0.07
    ote
    -0.07
    drink
    -0.07
     borders
    -0.07
    علوم
    -0.07
     Shortcut
    -0.07
    /Application
    -0.07
     Hanna
    -0.06
     Q
    -0.06
     localized
    -0.06
    POSITIVE LOGITS
    -next
    0.07
    +Sans
    0.06
    ียม
    0.06
     tanın
    0.06
    (Method
    0.06
     ylabel
    0.06
     aes
    0.06
    (material
    0.06
     přízn
    0.06
    _%
    0.06
    Act Density 0.011%

    No Known Activations