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

    Neuronpedia

    INDEX
    Explanations

    parentheses, brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Braz
    -0.07
     применения
    -0.07
    Ὀ
    -0.07
    (os
    -0.07
    /service
    -0.07
    私も
    -0.07
     Emperor
    -0.07
    作文
    -0.06
    🐐
    -0.06
     großen
    -0.06
    POSITIVE LOGITS
    peare
    0.07
    arin
    0.06
    ☺
    0.06
    сл
    0.06
    Credential
    0.06
    	endif
    0.06
     infinit
    0.06
    Equ
    0.06
    poons
    0.06
    _fw
    0.06
    Act Density 0.092%

    No Known Activations