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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the presence and attributes of various subjects, particularly in descriptive contexts

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

    "has" followed by an article

    np_acts-logits-general · gemini-2.0-flash

    existence of multiple items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.70
     obſ
    -0.62
     فريبيس
    -0.61
    readAs
    -0.59
    afficheront
    -0.59
    ambilan
    -0.58
     mortes
    -0.58
    UniformLocation
    -0.57
     houſe
    -0.57
     greateſt
    -0.56
    POSITIVE LOGITS
     a
    1.06
     lots
    0.93
     two
    0.81
     an
    0.80
     plenty
    0.79
     three
    0.76
     many
    0.74
     everything
    0.69
     four
    0.69
     several
    0.67
    Act Density 0.245%

    No Known Activations