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

    Neuronpedia

    INDEX
    Explanations

    Elon Musk ownership

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jdField
    0.48
     socios
    0.46
    }<\
    0.43
    縄
    0.43
    чно
    0.40
    στη
    0.40
    可行
    0.40
    ONTAL
    0.40
    த்திலும்
    0.39
     बेसिकली
    0.39
    POSITIVE LOGITS
     hoses
    0.44
     uds
    0.43
     millimeters
    0.43
    acion
    0.42
     모양
    0.42
    any
    0.41
    rhinoceros
    0.41
     axes
    0.39
     douceur
    0.39
     manches
    0.39
    Act Density 0.009%

    No Known Activations