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

    Neuronpedia

    INDEX
    Explanations

    issues related to conflicts and differences

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

    disputes and disagreements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     juſ
    -0.43
    addFlags
    -0.40
    Tetra
    -0.40
    atalos
    -0.40
     piti
    -0.40
    ousands
    -0.39
     decre
    -0.39
    regon
    -0.38
     Проци
    -0.38
    vician
    -0.38
    POSITIVE LOGITS
     dispute
    0.68
     disagreement
    0.66
     Dispute
    0.66
     disagreements
    0.65
     disputes
    0.61
     disagree
    0.59
     disagrees
    0.59
     Disputes
    0.58
     Disagree
    0.56
     disagreed
    0.52
    Act Density 0.178%

    No Known Activations