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

    Neuronpedia

    INDEX
    Explanations

    references to social media interactions and comments

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

    facebook posts containing names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.54
    oa̍t
    -0.50
    stateMutability
    -0.50
    請繼續往下閱讀
    -0.48
    木坂
    -0.47
     invokingState
    -0.46
    tvguidetime
    -0.45
     referrerpolicy
    -0.44
    ReusableCell
    -0.43
    nloa
    -0.43
    POSITIVE LOGITS
     facebook
    0.78
     Facebook
    0.77
    Facebook
    0.76
     Fb
    0.69
    facebook
    0.69
    FACEBOOK
    0.68
     FACEBOOK
    0.66
     fb
    0.65
     FB
    0.61
    fb
    0.58
    Act Density 0.008%

    No Known Activations