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

    Neuronpedia

    INDEX
    Explanations

    if you need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     now
    0.74
     Now
    0.69
    elson
    0.64
    iline
    0.63
    alle
    0.62
    inis
    0.62
    Now
    0.62
    ains
    0.61
    ine
    0.60
     Whatever
    0.59
    POSITIVE LOGITS
     intend
    0.86
     хотите
    0.82
    leece
    0.80
     algún
    0.78
     lenient
    0.78
     해당
    0.77
     multit
    0.76
     alguma
    0.76
    余裕
    0.76
     desean
    0.75
    Act Density 0.595%

    No Known Activations