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

    Neuronpedia

    INDEX
    Explanations

    Questions, code, examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manager
    -0.06
    -In
    -0.06
     crt
    -0.06
     cz
    -0.06
     poč
    -0.06
     изготов
    -0.06
    +(
    -0.06
    lake
    -0.06
     Night
    -0.06
     Skills
    -0.06
    POSITIVE LOGITS
    ahaha
    0.08
    家庭
    0.07
    _verified
    0.07
     выше
    0.06
     thuộc
    0.06
    ework
    0.06
    ',
↵
    0.06
    steps
    0.06
    тивного
    0.06
     learned
    0.06
    Act Density 0.001%

    No Known Activations