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

    Neuronpedia

    INDEX
    Explanations

    Colon punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exhaustion
    -0.07
    /connect
    -0.07
    .Re
    -0.06
    �单
    -0.06
     swelling
    -0.06
     onward
    -0.06
    	rep
    -0.06
    ospace
    -0.06
     promoter
    -0.06
    _lst
    -0.06
    POSITIVE LOGITS
    DSL
    0.07
    Verification
    0.06
    anteed
    0.06
     Cy
    0.06
    机
    0.06
     $"
    0.06
    ЛЬ
    0.06
    ALLY
    0.06
     manufactured
    0.06
    ään
    0.06
    Act Density 0.012%

    No Known Activations