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

    Neuronpedia

    INDEX
    Explanations

    the word "like" used as a hedge or qualifier

    oai_token-act-pair · gemini-2.0-flash

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -0.96
    tagHelperRunner
    -0.95
     like
    -0.89
    MLLoader
    -0.89
    ImageContext
    -0.82
     pinulongan
    -0.80
     kasarigan
    -0.76
     BorderSide
    -0.75
     Like
    -0.74
     fieldNum
    -0.73
    POSITIVE LOGITS
     such
    0.83
    Such
    0.79
    such
    0.78
     Such
    0.75
     solche
    0.66
     poche
    0.58
     SUCH
    0.56
     چنین
    0.56
     [*]
    0.56
     ilyen
    0.54
    Act Density 0.142%

    No Known Activations