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

    Neuronpedia

    INDEX
    Explanations

    -pre

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ayload
    -0.07
     的
    -0.06
     の
    -0.06
     Returns
    -0.06
    	boolean
    -0.06
    ropoda
    -0.06
     updating
    -0.06
     reproduce
    -0.06
     button
    -0.06
     elimin
    -0.06
    POSITIVE LOGITS
    álních
    0.08
     salle
    0.07
     Tues
    0.07
     pe
    0.07
     premi
    0.06
    κε
    0.06
    macen
    0.06
     Adri
    0.06
     üz
    0.06
    ��
    0.06
    Act Density 0.002%

    No Known Activations