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

    Neuronpedia

    INDEX
    Explanations

    scientific articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    63
    -0.07
     xor
    -0.06
     хорошо
    -0.06
     Standing
    -0.06
     آنها
    -0.06
     directly
    -0.06
    增加
    -0.06
     paris
    -0.06
     Nazis
    -0.06
     hunter
    -0.06
    POSITIVE LOGITS
    ‌پدیا
    0.07
    _insn
    0.06
     А
    0.06
    DMETHOD
    0.06
    gregated
    0.06
    _scalar
    0.06
     вал
    0.06
    Ин
    0.06
    esel
    0.06
    ADED
    0.06
    Act Density 0.053%

    No Known Activations