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

    Neuronpedia

    INDEX
    Explanations

    replacement and substitution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nameSort
    0.76
    ায়ত্ত
    0.72
    AxisSize
    0.70
     malu
    0.69
     categorization
    0.63
     collaborations
    0.63
    ណ្ឌ
    0.63
    chinen
    0.62
    olyb
    0.62
    絞
    0.62
    POSITIVE LOGITS
     replacement
    5.60
     replace
    5.52
     replacing
    5.25
     Replace
    5.24
     Replacement
    5.21
    Replace
    5.20
     replaces
    5.10
     replaced
    5.09
    replace
    5.08
     replacements
    5.06
    Act Density 0.903%

    No Known Activations