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

    Neuronpedia

    INDEX
    Explanations

    resource and industry production

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     verbal
    0.42
    临床
    0.40
     Variablen
    0.40
     Verbal
    0.39
     Sel
    0.37
     Notepad
    0.37
     Data
    0.37
     witty
    0.36
     Retro
    0.36
     Coding
    0.36
    POSITIVE LOGITS
     unsustainable
    0.63
    mining
    0.60
     mining
    0.58
     petrochemical
    0.57
     fossil
    0.57
     petroleum
    0.57
     pesticides
    0.54
    產業
    0.54
     производство
    0.53
     farming
    0.53
    Act Density 0.182%

    No Known Activations