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

    Neuronpedia

    INDEX
    Explanations

    designed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clears
    -0.07
    eful
    -0.07
     hashtable
    -0.06
    boom
    -0.06
    	for
    -0.06
     покуп
    -0.06
    ++]
    -0.06
    ;
↵
    -0.06
    }");
↵
    -0.06
     hangs
    -0.06
    POSITIVE LOGITS
    ออกแบบ
    0.07
     بهره
    0.06
    research
    0.06
     başlar
    0.06
    Delegate
    0.06
     Fraction
    0.06
    ridged
    0.06
    风险
    0.06
    _preferences
    0.06
     intended
    0.06
    Act Density 0.032%

    No Known Activations