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

    Neuronpedia

    INDEX
    Explanations

    demolish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جز
    -0.07
     成
    -0.07
    _te
    -0.06
    averse
    -0.06
     شب
    -0.06
    �
    -0.06
     روی
    -0.06
    泉
    -0.06
     Nicht
    -0.06
    winter
    -0.06
    POSITIVE LOGITS
     demolition
    0.15
     demol
    0.13
     demolished
    0.12
     surveyed
    0.07
     operation
    0.07
     survey
    0.07
     Tem
    0.07
     Survey
    0.07
    template
    0.07
    ovation
    0.06
    Act Density 0.006%

    No Known Activations