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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ())),
    -0.07
     wk
    -0.06
    .Chart
    -0.06
    �
    -0.06
    )];
    -0.06
     minus
    -0.06
     setUser
    -0.05
     }}}
    -0.05
    átka
    -0.05
    /cli
    -0.05
    POSITIVE LOGITS
    .ModelAdmin
    0.07
    -Za
    0.07
    	token
    0.06
     дослід
    0.06
    una
    0.06
     decree
    0.06
    cbd
    0.06
    	point
    0.06
     hack
    0.06
    영
    0.06
    Act Density 0.080%

    No Known Activations