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

    Neuronpedia

    INDEX
    Explanations

    Reserve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ָ
    -0.09
    -0.08
     anot
    -0.08
     Curse
    -0.08
     backpack
    -0.07
     Backpack
    -0.07
    ต่อ
    -0.07
     Explosion
    -0.07
    shopping
    -0.07
    ופש
    -0.07
    POSITIVE LOGITS
     Governors
    0.09
    制度
    0.08
     Mell
    0.08
     temperature
    0.08
    政策
    0.08
     mint
    0.08
     issuing
    0.08
     தலைவர்
    0.08
     governor
    0.08
    Instit
    0.08
    Act Density 0.009%
    No Known Activations