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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     застав
    -0.07
     darken
    -0.06
    critical
    -0.06
     baths
    -0.06
    plant
    -0.06
    การพ
    -0.06
     Windsor
    -0.06
     bath
    -0.06
    	cell
    -0.06
    ansible
    -0.06
    POSITIVE LOGITS
    였
    0.08
     Evropy
    0.07
    }">↵
    0.07
     wasting
    0.06
    ’↵↵
    0.06
    ูแล
    0.06
    上海
    0.06
    "},↵
    0.06
    _children
    0.06
     hiểm
    0.06
    Act Density 0.043%

    No Known Activations