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

    Neuronpedia

    INDEX
    Explanations

    indicates "ate"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lauded
    0.48
    此前
    0.45
    णे
    0.44
    ޘ
    0.44
     discovers
    0.43
    ീല
    0.42
    ધન
    0.42
     нём
    0.42
     discovered
    0.41
    発見
    0.41
    POSITIVE LOGITS
    nil
    0.58
    c
    0.57
    slow
    0.56
    acet
    0.56
    or
    0.54
    cast
    0.54
    friendly
    0.52
    mer
    0.51
    cad
    0.51
    neutral
    0.51
    Act Density 0.003%

    No Known Activations