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

    Neuronpedia

    INDEX
    Explanations

    "let's " contraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Input
    0.28
     compute
    0.27
     computes
    0.26
     Application
    0.25
     input
    0.25
     THEN
    0.25
     Compute
    0.25
     Base
    0.25
     Response
    0.25
     Output
    0.25
    POSITIVE LOGITS
    नेक
    0.27
    कोल
    0.26
    बहुत
    0.26
    لاه
    0.25
    న్నీ
    0.25
    ően
    0.25
    ני
    0.24
     شهر
    0.24
    Omar
    0.23
     დიდი
    0.23
    Act Density 0.082%

    No Known Activations