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

    Neuronpedia

    INDEX
    Explanations

    Places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <!
    -0.06
    .amazon
    -0.06
     как
    -0.06
    ポイント
    -0.06
    θεί
    -0.06
     gren
    -0.06
    ******↵↵
    -0.06
     ・
    -0.05
    _AMD
    -0.05
    ↵	
↵
    -0.05
    POSITIVE LOGITS
    _GT
    0.07
     Parent
    0.06
     muscular
    0.06
     Austin
    0.06
    .colors
    0.06
     preservation
    0.06
    .SUCCESS
    0.06
     Norte
    0.06
     airstrikes
    0.06
    Nut
    0.06
    Act Density 0.075%

    No Known Activations