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

    Neuronpedia

    INDEX
    Explanations

    InView

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kk
    -0.06
    	client
    -0.06
     siege
    -0.06
    been
    -0.06
    .have
    -0.06
     •
    -0.06
     persons
    -0.06
    recipes
    -0.06
    ponent
    -0.06
     οι
    -0.06
    POSITIVE LOGITS
     girdi
    0.07
     Dorm
    0.07
     SignUp
    0.06
     zav
    0.06
     Invitation
    0.06
     Cougar
    0.06
     Dram
    0.06
     signUp
    0.06
     Thur
    0.06
    Phoenix
    0.06
    Act Density 0.000%

    No Known Activations