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

    Neuronpedia

    INDEX
    Explanations

    string concatenation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _='
    0.48
     belladone
    0.47
    唥
    0.46
    _="
    0.45
    রদ্ব
    0.45
    renerg
    0.44
    Walt
    0.44
    ثیر
    0.43
    ્વાસ
    0.43
     nisid
    0.43
    POSITIVE LOGITS
     To
    0.46
     concat
    0.43
     +
    0.42
     A
    0.42
     followed
    0.42
     So
    0.41
    да
    0.41
     join
    0.41
    concat
    0.40
     No
    0.40
    Act Density 0.009%

    No Known Activations