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

    Neuronpedia

    INDEX
    Explanations

    code and technical text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wisely
    -0.07
     Hot
    -0.07
    fect
    -0.07
     scm
    -0.07
     pursuing
    -0.06
     altura
    -0.06
     kvinn
    -0.06
     eser
    -0.06
    latent
    -0.06
    اسر
    -0.06
    POSITIVE LOGITS
    воб
    0.06
    :System
    0.06
     nieuwe
    0.06
     коль
    0.06
    _Save
    0.06
    ÖL
    0.06
    @Web
    0.06
    XC
    0.06
     dein
    0.06
     свидетель
    0.06
    Act Density 0.000%

    No Known Activations