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

    Neuronpedia

    INDEX
    Explanations

    Recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ten
    -0.07
    脚
    -0.07
    	graph
    -0.07
    pipes
    -0.07
    Token
    -0.07
    社
    -0.07
     pago
    -0.07
     Nag
    -0.06
     polls
    -0.06
     Benn
    -0.06
    POSITIVE LOGITS
    UEL
    0.07
     Excellent
    0.07
     embark
    0.06
    /gcc
    0.06
    allowed
    0.06
     extrem
    0.06
     опас
    0.06
    цик
    0.06
    /rc
    0.06
    preserve
    0.06
    Act Density 0.007%

    No Known Activations