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

    Neuronpedia

    INDEX
    Explanations

    legal, presumed innocence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ing
    -0.07
     připoj
    -0.07
     том
    -0.07
     IMO
    -0.06
    लग
    -0.06
    رك
    -0.06
    έρει
    -0.06
    ighted
    -0.06
     sonrası
    -0.06
     rightly
    -0.06
    POSITIVE LOGITS
     бізнес
    0.08
     REST
    0.06
    	res
    0.06
     Kil
    0.06
    prene
    0.06
    %"),↵
    0.06
    esinin
    0.06
     Chancellor
    0.06
     enchanted
    0.06
     перен
    0.06
    Act Density 0.003%

    No Known Activations