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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoiding
    -0.06
     Healthcare
    -0.06
     Behind
    -0.06
     screenshot
    -0.06
    buttons
    -0.06
    leads
    -0.06
     получения
    -0.06
     Yang
    -0.06
     inequality
    -0.06
     useful
    -0.06
    POSITIVE LOGITS
     berhasil
    0.07
     Влади
    0.06
     OkHttpClient
    0.06
    �
    0.06
    čem
    0.06
     BITTE
    0.06
     AudioSource
    0.06
    teenth
    0.06
    ordinated
    0.06
     mænd
    0.06
    Act Density 0.024%

    No Known Activations