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

    Neuronpedia

    INDEX
    Explanations

    events or specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ა
    0.50
     LPTMR
    0.45
    únior
    0.45
     lathe
    0.44
    ла
    0.43
    rž
    0.43
    ାନ
    0.43
     आहेत
    0.42
     සම්
    0.42
    父親
    0.42
    POSITIVE LOGITS
     Event
    0.47
    搞
    0.46
     Assassin
    0.45
    事件
    0.44
    Events
    0.44
    this
    0.43
     Events
    0.43
     ismi
    0.43
     okaza
    0.43
     Error
    0.42
    Act Density 0.006%

    No Known Activations