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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cerco
    -0.07
    がない
    -0.07
    清朝
    -0.06
    ig
    -0.06
     mét
    -0.06
    (pipe
    -0.06
    初二
    -0.06
    豺
    -0.06
    finance
    -0.06
    增大
    -0.06
    POSITIVE LOGITS
    ║
    0.07
    ☠
    0.07
     trữ
    0.07
    調
    0.07
     CONTROL
    0.07
    LM
    0.07
    zel
    0.07
    Compatible
    0.07
    HZ
    0.07
    comfort
    0.06
    Act Density 0.003%

    No Known Activations