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

    Neuronpedia

    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blockers
    -0.07
    ists
    -0.07
    apped
    -0.07
    笯
    -0.07
    ист
    -0.07
    ist
    -0.07
     Sor
    -0.06
    ista
    -0.06
    迓
    -0.06
     alk
    -0.06
    POSITIVE LOGITS
     nắng
    0.07
     LX
    0.07
     Thư
    0.06
    롤
    0.06
    佚
    0.06
     سريع
    0.06
    _paths
    0.06
    ألوان
    0.06
     lxml
    0.06
    初三
    0.06
    Act Density 0.001%

    No Known Activations