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

    Neuronpedia

    INDEX
    Explanations

    sentences that include the word "find", other related words, and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    find

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.69
    Way
    -0.67
    Бахар
    -0.66
    way
    -0.65
     Way
    -0.64
    stdc
    -0.62
    WAY
    -0.59
     way
    -0.59
    RectangleBorder
    -0.57
    afficheront
    -0.57
    POSITIVE LOGITS
     puissiez
    0.66
     $_
    0.57
     Cæsar
    0.55
    Tokenizer
    0.52
     Frogs
    0.51
    s
    0.48
     Mauritania
    0.47
     frogs
    0.47
     monasteries
    0.46
    áctenos
    0.46
    Act Density 12.444%

    No Known Activations