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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ////↵
    -0.06
     захід
    -0.06
    TYPO
    -0.06
     Plaint
    -0.06
    rowad
    -0.06
    otřeb
    -0.06
    expects
    -0.06
     others
    -0.06
    isdigit
    -0.06
     TextEditingController
    -0.06
    POSITIVE LOGITS
     Relation
    0.07
     Meet
    0.07
    _bi
    0.07
    ONE
    0.07
     fine
    0.07
     Odd
    0.07
    amily
    0.06
    OB
    0.06
    완
    0.06
    Close
    0.06
    Act Density 0.023%

    No Known Activations