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

    Neuronpedia

    INDEX
    Explanations

    various environments and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    9
    0.66
    8
    0.65
    5
    0.63
    7
    0.62
    6
    0.59
    ↵
    0.56
    4
    0.52
    i
    0.50
    P
    0.49
    up
    0.49
    POSITIVE LOGITS
     まとめ
    0.54
     hermaph
    0.51
     灬
    0.50
    拠
    0.49
     ਨਾਲ
    0.48
    notlocked
    0.48
     Comprom
    0.48
     Allowance
    0.47
     Expenditure
    0.47
    鋲
    0.47
    Act Density 0.000%

    No Known Activations