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

    Neuronpedia

    INDEX
    Explanations

    bleak, can be often, without meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ದ
    0.66
     vouch
    0.47
     nieuwe
    0.45
    어
    0.44
     Accesat
    0.44
    acci
    0.43
     riguardo
    0.43
    ธรรม
    0.43
     Ново
    0.43
    VARCHAR
    0.43
    POSITIVE LOGITS
    ເລັກ
    0.45
     leveling
    0.42
    љено
    0.42
     спине
    0.42
     arası
    0.41
     lý
    0.40
     inspiring
    0.40
     lev
    0.40
    endTime
    0.40
    b
    0.40
    Act Density 0.001%

    No Known Activations