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

    Neuronpedia

    INDEX
    Explanations

    descriptive words and sensory details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    快乐
    0.54
     अद्भुत
    0.50
    ículo
    0.49
    Adorable
    0.49
    íguez
    0.48
    havior
    0.47
    ání
    0.46
    Okno
    0.46
    Cruz
    0.46
    RefManager
    0.45
    POSITIVE LOGITS
     then
    0.44
     filenames
    0.43
     timescales
    0.42
     x
    0.41
     bays
    0.41
     shorts
    0.41
     Germany
    0.40
     Spain
    0.40
    servername
    0.39
     spy
    0.39
    Act Density 0.000%

    No Known Activations