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

    Neuronpedia

    INDEX
    Explanations

    human activities and their impacts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mentoring
    0.78
     mentors
    0.75
    unteers
    0.72
     faculty
    0.72
     escrow
    0.71
     Junior
    0.71
     Obama
    0.70
    股权
    0.70
     professors
    0.68
     Automat
    0.68
    POSITIVE LOGITS
     anthropogenic
    1.54
     deforestation
    1.48
     urbanization
    1.47
     industrial
    1.17
     industrialized
    1.15
     pollution
    1.14
    artificial
    1.11
     artificial
    1.10
     manusia
    1.08
     overuse
    1.07
    Act Density 0.141%

    No Known Activations