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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    F
    -0.07
    _DF
    -0.07
     označ
    -0.06
     黑
    -0.06
     Это
    -0.06
    �ng
    -0.06
     timp
    -0.06
     cred
    -0.06
     G
    -0.06
     vmin
    -0.06
    POSITIVE LOGITS
    нуть
    0.07
     khối
    0.07
     проекту
    0.07
    voří
    0.07
     дій
    0.07
    ovaly
    0.07
    argins
    0.06
     trä
    0.06
     примі
    0.06
    _detect
    0.06
    Act Density 0.004%

    No Known Activations