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

    Neuronpedia

    INDEX
    Explanations

    Database connection code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    少女
    -0.07
    耀眼
    -0.07
     Ralph
    -0.07
    dhcp
    -0.06
    赞叹
    -0.06
     filled
    -0.06
     technological
    -0.06
     Orch
    -0.06
    -faced
    -0.06
     items
    -0.06
    POSITIVE LOGITS
    طول
    0.07
    كا
    0.07
     sights
    0.06
    ינו
    0.06
     Hoover
    0.06
    昆
    0.06
    \',
    0.06
    금
    0.06
    骒
    0.06
    reed
    0.06
    Act Density 0.005%

    No Known Activations