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

    Neuronpedia

    INDEX
    Explanations

    verbs matching contractions such as "it's", "that's", "aren't", or the word "isn't"

    oai_token-act-pair · gemini-2.0-flash

    words ending in "ly"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.82
    almost
    -0.81
     almost
    -0.79
    RenderAtEndOf
    -0.79
     Slightly
    -0.79
     TAMBIÉN
    -0.73
    Slightly
    -0.71
    Almost
    -0.71
     somewhat
    -0.71
     سكانية
    -0.70
    POSITIVE LOGITS
     necessarily
    0.91
     necessariamente
    0.82
    necessarily
    0.71
     necesariamente
    0.68
     anymore
    0.58
     sepenuhnya
    0.54
     nécessairement
    0.54
     immune
    0.53
     entirely
    0.53
     exatamente
    0.52
    Act Density 7.848%

    No Known Activations