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

    Neuronpedia

    INDEX
    Explanations

    TODO or Todoist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ỡng
    0.38
    
    0.38
    اهده
    0.38
    nije
    0.38
     אחרי
    0.38
     सावधानी
    0.38
     hypocrisy
    0.38
    ativity
    0.37
     छोटा
    0.37
    летний
    0.37
    POSITIVE LOGITS
    リスト
    0.41
    NA
    0.38
     inhib
    0.38
     TODO
    0.38
     parametrization
    0.37
     inline
    0.36
    dist
    0.35
    BW
    0.35
     দলীয়
    0.35
     prohibitive
    0.35
    Act Density 0.001%

    No Known Activations