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

    Neuronpedia

    INDEX
    Explanations

    destruction and damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َم
    -0.07
    _toolbar
    -0.07
     CONTACT
    -0.07
    ║
    -0.06
    _printf
    -0.06
    ology
    -0.06
    (ship
    -0.06
    IVATE
    -0.06
     нар
    -0.06
    tadır
    -0.06
    POSITIVE LOGITS
    」↵
    0.06
     thousands
    0.06
     electrode
    0.06
     HISTORY
    0.06
     tarih
    0.06
     سال
    0.06
     Gong
    0.06
     своим
    0.06
     Cy
    0.06
    ";↵↵↵
    0.06
    Act Density 0.035%

    No Known Activations