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

    Neuronpedia

    INDEX
    Explanations

    themes of protection and strongholds

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

    fortress or cautious

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.60
    帖最后由
    -0.60
     sexes
    -0.59
     endfor
    -0.56
     getItemId
    -0.54
    testify
    -0.54
     Sumit
    -0.54
     Inscrivez
    -0.53
     PopupWindow
    -0.53
    InSection
    -0.53
    POSITIVE LOGITS
     Fortress
    0.71
     fortress
    0.70
     cloak
    0.66
    cloak
    0.60
     Cloak
    0.56
    GTCX
    0.52
    mati
    0.42
     embrace
    0.42
    <bos>
    0.42
    istungs
    0.40
    Act Density 0.005%

    No Known Activations