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

    Neuronpedia

    INDEX
    Explanations

    negations and strong assertions

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

    no + auxiliary verb + subject

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Roads
    -0.45
    roads
    -0.45
     Uda
    -0.44
     roads
    -0.41
     Vet
    -0.37
    Routes
    -0.35
     borders
    -0.35
     Heat
    -0.35
    Roads
    -0.35
     bef
    -0.35
    POSITIVE LOGITS
    存于互联网档案馆
    0.60
    rungsseite
    0.59
    httphttps
    0.49
    Cyfarwyddwr
    0.47
     BoxFit
    0.46
    Šaltiniai
    0.45
    enterOuterAlt
    0.45
    новништво
    0.44
     onBackPressed
    0.43
    Referensi
    0.43
    Act Density 0.052%

    No Known Activations