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

    Neuronpedia

    INDEX
    Explanations

    this is new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лянчук
    0.42
    бора
    0.39
    तरे
    0.38
     분야
    0.37
     	i
    0.37
     речь
    0.36
    ğrafl
    0.36
    curricular
    0.35
    첵
    0.35
    ंछ
    0.35
    POSITIVE LOGITS
     myriad
    0.48
     multitude
    0.39
     Needless
    0.39
     plethora
    0.38
     Token
    0.38
     amic
    0.38
     scenes
    0.37
    www
    0.37
     handful
    0.37
     new
    0.37
    Act Density 0.086%

    No Known Activations