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

    Neuronpedia

    INDEX
    Explanations

    let's start with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     continuidad
    0.45
     technik
    0.45
    freund
    0.41
    usi
    0.41
    lemente
    0.40
    świet
    0.40
    än
    0.39
    сно
    0.39
    far
    0.39
     временем
    0.39
    POSITIVE LOGITS
     και
    0.47
    和
    0.46
     आणि
    0.45
     suffice
    0.43
    了一個
    0.43
     અને
    0.42
    獎
    0.42
    まずは
    0.41
    匱
    0.41
     மற்றும்
    0.41
    Act Density 0.002%

    No Known Activations