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

    Neuronpedia

    INDEX
    Explanations

    re- words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    0.45
    4
    0.44
     A
    0.42
     is
    0.42
     L
    0.40
    k
    0.40
     I
    0.38
     )
    0.37
    0.37
    kult
    0.36
    POSITIVE LOGITS
    מו
    0.52
    ने
    0.50
    行う
    0.48
    oretically
    0.48
    ку
    0.47
    ق
    0.46
    kan
    0.45
    can
    0.45
    ності
    0.44
     can
    0.43
    Act Density 0.021%

    No Known Activations