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

    Neuronpedia

    INDEX
    Explanations

    concentration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alteration
    -0.07
    елей
    -0.06
     defended
    -0.06
    _Frame
    -0.06
    Pinterest
    -0.06
     पत
    -0.06
    	void
    -0.06
     neoliberal
    -0.06
     стен
    -0.06
     маль
    -0.06
    POSITIVE LOGITS
    Jake
    0.07
     Oct
    0.06
    ％
    0.06
    нд
    0.06
    oir
    0.06
    -alert
    0.06
     нож
    0.06
     Tata
    0.06
     pasar
    0.06
    -ни
    0.06
    Act Density 0.015%

    No Known Activations