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

    Neuronpedia

    INDEX
    Explanations

    expressions of strong emotional responses and attitudes towards personal beliefs

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

    Informal online communication

    np_acts-logits-general · gemini-2.0-flash

    positive expressions and personal identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.74
     = 
    -0.73
    WaitGroup
    -0.70
    ]-->
    -0.68
    AsUp
    -0.64
    ;-)
    -0.61
    
    -0.60
     ;-)
    -0.59
     CHtml
    -0.59
     ‪
    -0.57
    POSITIVE LOGITS
    ptid
    0.68
     🥺
    0.67
     idk
    0.65
     queer
    0.65
     abt
    0.63
     bc
    0.61
     uw
    0.60
     Idk
    0.59
    呜呜
    0.57
     lesbian
    0.57
    Act Density 0.072%

    No Known Activations