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

    Neuronpedia

    INDEX
    Explanations

    Giving examples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fighters
    -0.07
    крет
    -0.07
    ในร
    -0.07
    orElse
    -0.07
    .onerror
    -0.06
     Ships
    -0.06
     subcontract
    -0.06
     flows
    -0.06
    -containing
    -0.06
    rama
    -0.06
    POSITIVE LOGITS
    oshi
    0.07
    WINDOWS
    0.07
    /"+
    0.07
    ).*
    0.06
    .io
    0.06
    ecast
    0.06
    اگ
    0.06
    ып
    0.06
    ']=
    0.06
    んで
    0.06
    Act Density 0.102%

    No Known Activations