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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Here."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Here" followed by "is," "are," or a punctuation

    np_acts-logits-general · gemini-2.0-flash

    here introducing lists or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sterious
    -0.67
    nalité
    -0.63
     vPvB
    -0.63
    RegressionTest
    -0.61
    twimg
    -0.60
     makeStyles
    -0.58
     SafeMath
    -0.58
     LSM
    -0.58
     CreateTagHelper
    -0.57
    }{*}{
    -0.56
    POSITIVE LOGITS
    Here
    0.75
     Here
    0.73
    here
    0.63
     HERE
    0.62
    Heres
    0.59
     here
    0.59
    fordshire
    0.58
     Hereford
    0.56
    HERE
    0.55
    tical
    0.52
    Act Density 0.059%

    No Known Activations