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

    Neuronpedia

    INDEX
    Explanations

    descriptive and conditional phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Donate
    0.47
     revamped
    0.44
     Neighborhood
    0.44
     neighborhoods
    0.44
     communities
    0.43
    親
    0.43
     intercultural
    0.43
     nonprofits
    0.42
     Donation
    0.42
    ড়ি
    0.42
    POSITIVE LOGITS
     possibilities
    0.41
    doesn
    0.40
    when
    0.40
    itsu
    0.40
    classify
    0.39
    keen
    0.39
     असताना
    0.38
     opts
    0.38
    წერ
    0.38
     defies
    0.38
    Act Density 0.000%

    No Known Activations