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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    լ
    -0.08
     True
    -0.07
    .ob
    -0.07
     гол
    -0.07
     introductory
    -0.07
     Pre
    -0.06
    🎿
    -0.06
    Principal
    -0.06
     المه
    -0.06
     TextArea
    -0.06
    POSITIVE LOGITS
     orbit
    0.07
     irony
    0.07
     demise
    0.06
     forgiving
    0.06
     newline
    0.06
     نها
    0.06
     giant
    0.06
    uder
    0.06
    America
    0.06
     outlaw
    0.06
    Act Density 0.010%

    No Known Activations