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

    Neuronpedia

    INDEX
    Explanations

    always

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    REAK
    -0.07
     thrown
    -0.07
     hostile
    -0.07
    EIF
    -0.06
    bed
    -0.06
    ...,
    -0.06
     shuffle
    -0.06
    courses
    -0.06
     alarmed
    -0.06
     كانت
    -0.06
    POSITIVE LOGITS
     الشيخ
    0.08
    ApiController
    0.07
    AdminController
    0.07
     objedn
    0.06
     Carla
    0.06
    'name
    0.06
     та
    0.06
    सभ
    0.06
    一直
    0.06
     zaten
    0.06
    Act Density 0.005%

    No Known Activations