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

    Neuronpedia

    INDEX
    Explanations

    say ":"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _warning
    -0.07
     User
    -0.06
    Hair
    -0.06
     وضع
    -0.06
     twelve
    -0.06
     photon
    -0.06
     write
    -0.06
    ientes
    -0.06
    .false
    -0.06
     différent
    -0.06
    POSITIVE LOGITS
     دانشجوی
    0.07
    enis
    0.06
    VertexUvs
    0.06
    SSION
    0.06
     Maul
    0.06
    ΕΙ
    0.06
     الاس
    0.06
     Citadel
    0.06
    _constants
    0.06
     предус
    0.06
    Act Density 0.002%

    No Known Activations