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

    Neuronpedia

    INDEX
    Explanations

    links starting with https

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lbs
    0.31
    _
    0.30
     management
    0.24
     admir
    0.24
     gradu
    0.24
    ��
    0.23
     seism
    0.23
     lute
    0.23
     climat
    0.23
     mô
    0.23
    POSITIVE LOGITS
    ково
    0.26
    以往
    0.25
     আরম্ভ
    0.25
    рис
    0.25
    ългар
    0.25
    йон
    0.25
     AppleWebKit
    0.24
    ето
    0.24
    https
    0.24
    כת
    0.24
    Act Density 0.090%

    No Known Activations