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

    Neuronpedia

    INDEX
    Explanations

    line breaks and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     probabilistic
    0.51
     alloys
    0.48
     DeFi
    0.45
     maquill
    0.45
     memilih
    0.44
     ALLOYS
    0.44
     SMART
    0.43
     Bayesian
    0.43
     ASK
    0.43
     RANDOM
    0.42
    POSITIVE LOGITS
     separator
    0.84
     indentation
    0.71
    separator
    0.69
    分隔
    0.68
    Newline
    0.68
     spacing
    0.67
    newLine
    0.65
    NewLine
    0.65
    Separator
    0.64
     separators
    0.62
    Act Density 0.267%

    No Known Activations