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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    396
    -0.06
    Zone
    -0.06
     NOTICE
    -0.06
     Katz
    -0.06
    Appointment
    -0.06
    376
    -0.06
    =E
    -0.06
     Late
    -0.06
     poměr
    -0.06
    formik
    -0.06
    POSITIVE LOGITS
    texture
    0.06
    Nd
    0.06
    bies
    0.06
    administr
    0.06
    promotion
    0.06
     dél
    0.06
     durumu
    0.06
     pasa
    0.06
    _motor
    0.06
     most
    0.06
    Act Density 0.011%

    No Known Activations