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

    Neuronpedia

    INDEX
    Explanations

    availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    й
    1.45
    ి
    1.34
    س
    1.31
    𝑠
    1.25
    𝐧
    1.20
    𝐥
    1.19
    ામ
    1.18
    🅐
    1.17
    𝐝
    1.17
    UIAlert
    1.17
    POSITIVE LOGITS
     कराए
    1.31
    ৈধ
    1.25
    ties
    1.22
     prises
    1.16
    in
    1.15
     продаже
    1.13
    стоя
    1.09
    كم
    1.08
     कराया
    1.07
    glichkeiten
    1.06
    Act Density 0.062%

    No Known Activations