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

    Neuronpedia

    INDEX
    Explanations

    nature of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Version
    0.46
     Valid
    0.46
    dx
    0.44
     Perspective
    0.43
     Vibes
    0.43
     версию
    0.42
     version
    0.41
    বাব
    0.40
     Ade
    0.40
     adequacy
    0.40
    POSITIVE LOGITS
     вещей
    0.50
    tson
    0.43
    ቾ
    0.40
     χαρακ
    0.39
     resultContent
    0.39
     testclass
    0.38
     характера
    0.38
    <unused2200>
    0.38
     staggered
    0.38
    დეს
    0.37
    Act Density 0.010%

    No Known Activations