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

    Neuronpedia

    INDEX
    Explanations

    prepositions, punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _iteration
    -0.07
    807
    -0.06
    ूचन
    -0.06
     expecting
    -0.06
    .To
    -0.06
    ereo
    -0.06
     Sala
    -0.06
    ужд
    -0.06
    Alg
    -0.06
    _yield
    -0.06
    POSITIVE LOGITS
     김
    0.07
    افی
    0.07
    세
    0.07
    سطس
    0.07
    虚
    0.06
    нет
    0.06
     희
    0.06
     matt
    0.06
    .align
    0.06
     personel
    0.06
    Act Density 0.096%

    No Known Activations