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

    Neuronpedia

    INDEX
    Explanations

    Formal text/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pipes
    -0.06
    Guest
    -0.06
    strain
    -0.06
    ẳ
    -0.06
     ankles
    -0.06
     potent
    -0.06
    ансов
    -0.06
     miserable
    -0.06
    lland
    -0.06
    .Parent
    -0.06
    POSITIVE LOGITS
     gái
    0.07
    _DI
    0.07
    (height
    0.07
     gele
    0.07
     पर
    0.06
    _signal
    0.06
    .setRotation
    0.06
     etwas
    0.06
     س
    0.06
    čky
    0.06
    Act Density 0.023%

    No Known Activations