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

    Neuronpedia

    INDEX
    Explanations

    attered

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utf
    -0.06
    rne
    -0.06
    yasal
    -0.06
    _literal
    -0.06
     Arabian
    -0.06
    _samples
    -0.06
    (AdapterView
    -0.06
    ------
    -0.06
    изнес
    -0.06
    (search
    -0.06
    POSITIVE LOGITS
    /bus
    0.07
    σκε
    0.07
     honour
    0.07
     honored
    0.07
    攻击
    0.07
     honoured
    0.07
    Too
    0.06
     SP
    0.06
    シー
    0.06
    svp
    0.06
    Act Density 0.013%

    No Known Activations