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

    Neuronpedia

    INDEX
    Explanations

    Two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gu
    -0.07
    #@
    -0.07
     квіт
    -0.06
    wizard
    -0.06
     Modelo
    -0.06
    tested
    -0.06
     deal
    -0.06
    Phase
    -0.06
     sliders
    -0.06
     kannst
    -0.06
    POSITIVE LOGITS
     vo
    0.07
     apprentices
    0.07
     �
    0.07
     بين
    0.06
     ชนะ
    0.06
    /security
    0.06
    ={"/
    0.06
     militias
    0.06
     exposition
    0.06
     Loot
    0.06
    Act Density 0.015%

    No Known Activations