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

    Neuronpedia

    INDEX
    Explanations

    programming code segments

    np_acts-logits-general · gemini-2.5-flash-lite

    lines of source code or programming-related tokens (code keywords, identifiers, and comments).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
      
    0.24
    或者
    0.21
    KY
    0.21
     Shit
    0.21
                                
    0.21
     OK
    0.20
       
    0.20
    [
    0.20
     FAT
    0.20
                     
    0.20
    POSITIVE LOGITS
     powiedział
    0.34
    رآ
    0.33
     fakat
    0.32
     बीते
    0.32
     añadió
    0.31
     aquel
    0.31
     bastante
    0.30
     довольно
    0.30
     canción
    0.30
     cependant
    0.30
    Act Density 1.577%

    No Known Activations