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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tasmania
    -0.07
     Resume
    -0.06
     Vacation
    -0.06
    _lst
    -0.06
    лекс
    -0.06
     z
    -0.06
     “
    -0.06
     مدير
    -0.06
     Parish
    -0.06
    >New
    -0.06
    POSITIVE LOGITS
     ToString
    0.07
    �
    0.07
    dragon
    0.06
    agen
    0.06
     Should
    0.06
    ียง
    0.06
    _ELEMENTS
    0.06
     Expansion
    0.06
    imat
    0.06
    äsent
    0.06
    Act Density 0.010%

    No Known Activations