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

    Neuronpedia

    INDEX
    Explanations

    references to tables

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

    "Table" followed by other tokens or characters

    np_acts-logits-general · gemini-2.0-flash

    Table followed by identifier or description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.67
    asteroide
    -0.56
     متعلقه
    -0.53
    väg
    -0.52
     Spent
    -0.48
    ]--;
    -0.47
    ärke
    -0.47
    umbing
    -0.46
    หวัด
    -0.46
    Taz
    -0.45
    POSITIVE LOGITS
    tennis
    0.81
    cloths
    0.80
    tops
    0.78
     tennis
    0.75
    cloth
    0.73
     Tennis
    0.68
    Tennis
    0.67
    top
    0.66
    aux
    0.66
    ENNIS
    0.64
    Act Density 0.123%

    No Known Activations