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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "discovery" and related phrases indicating new findings

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

    reporting scientific discoveries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.59
    󰀄
    -0.57
     صفحۀ
    -0.53
     IFTT
    -0.53
    elang
    -0.50
    mainAxisSize
    -0.50
    metra
    -0.49
    bootstrapcdn
    -0.48
    asantry
    -0.48
    xase
    -0.48
    POSITIVE LOGITS
     discovery
    1.10
     discoveries
    1.06
     descubrimiento
    0.89
     découverte
    0.88
     discovered
    0.85
     scoperta
    0.83
     desco
    0.81
     odkry
    0.81
    discovery
    0.80
     découvertes
    0.79
    Act Density 0.036%

    No Known Activations