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

    Neuronpedia

    INDEX
    Explanations

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     have
    0.64
    have
    0.60
    -
    0.48
    Have
    0.45
     haue
    0.43
    ين
    0.42
     as
    0.41
            
    0.41
     Have
    0.40
    其他
    0.40
    POSITIVE LOGITS
                
    0.46
    il
    0.46
    .";
    0.45
    ти
    0.45
     ۳
    0.45
    rhein
    0.44
    ا۔
    0.44
    ３
    0.44
    ។
    0.44
    ле
    0.43
    Act Density 0.119%

    No Known Activations