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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to positive experiences and attitudes

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

    positive emotions or attitudes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ditem
    -0.33
     specifications
    -0.33
     liquid
    -0.32
     consulting
    -0.31
    berapa
    -0.31
     αι
    -0.31
     them
    -0.31
     exquisite
    -0.31
     eksper
    -0.30
    Біографія
    -0.30
    POSITIVE LOGITS
    Positive
    1.04
     positivity
    1.01
    positive
    0.95
     positive
    0.94
     Positive
    0.94
     positivas
    0.88
     POSITIVE
    0.87
     negativity
    0.87
    POSITIVE
    0.85
     positiva
    0.81
    Act Density 0.020%

    No Known Activations