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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity and straightforwardness

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

    clear understanding or directions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.47
     استنادى
    -0.43
    bootstrapcdn
    -0.41
     instalação
    -0.40
    Aiheesta
    -0.38
     EconPapers
    -0.37
     resorts
    -0.36
     vouch
    -0.36
    solete
    -0.35
    湊
    -0.35
    POSITIVE LOGITS
    Clear
    1.17
     clear
    1.16
     Clear
    1.12
    clear
    1.12
     clarity
    1.04
     clearly
    1.00
     CLEAR
    0.99
    CLEAR
    0.97
     clearest
    0.97
     chiara
    0.96
    Act Density 0.024%

    No Known Activations