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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    configured
    -0.06
    "),↵
    -0.06
     landmark
    -0.06
    .cvtColor
    -0.06
    _encrypt
    -0.06
     miserable
    -0.06
    скую
    -0.06
                                                    ↵
    -0.06
     designed
    -0.06
     CJ
    -0.06
    POSITIVE LOGITS
    аться
    0.07
    �
    0.07
    龄
    0.07
     Guinea
    0.07
    意味
    0.06
    emma
    0.06
     Jeremiah
    0.06
    )throws
    0.06
     बढ़
    0.06
     وظ
    0.06
    Act Density 0.003%

    No Known Activations