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

    Neuronpedia

    INDEX
    Explanations

    Code, mixed languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distract
    -0.08
    	virtual
    -0.07
    	a
    -0.06
     DFA
    -0.06
     Friedman
    -0.06
     Applicant
    -0.06
    Translated
    -0.06
     Giul
    -0.06
     لیگ
    -0.06
     Dolphin
    -0.06
    POSITIVE LOGITS
    ogenesis
    0.06
     '_'
    0.06
    енном
    0.06
    ové
    0.06
    ainties
    0.06
     Approval
    0.06
    811
    0.06
     Hack
    0.06
    prints
    0.06
    ／↵
    0.06
    Act Density 0.000%

    No Known Activations