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
     Latest
    -0.07
    Ring
    -0.07
    /member
    -0.07
    .salary
    -0.07
    Zip
    -0.07
    温
    -0.07
    	Message
    -0.06
    Tek
    -0.06
    ًا
    -0.06
    _PAY
    -0.06
    POSITIVE LOGITS
     inadvertently
    0.07
    uvre
    0.06
     usize
    0.06
    ��
    0.06
     bağır
    0.06
    ινη
    0.06
    чила
    0.05
     ancient
    0.05
     مت
    0.05
    unte
    0.05
    Act Density 0.000%

    No Known Activations