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

    Neuronpedia

    INDEX
    Explanations

    Mod or Ter suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     GME
    -0.87
     proportionality
    -0.83
    чила
    -0.78
    ʀ
    -0.78
    operative
    -0.78
     CHtml
    -0.77
     NOK
    -0.77
    φαλ
    -0.75
    ılık
    -0.75
     gesuchten
    -0.75
    POSITIVE LOGITS
     features
    0.80
    Apri
    0.77
     hepat
    0.76
     forskj
    0.72
     tämä
    0.71
     cáo
    0.69
     Burgen
    0.68
     Features
    0.67
    горе
    0.67
     Росси
    0.66
    Act Density 0.005%

    No Known Activations