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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to notable actions or classifications

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

    Non-English words and abbreviations

    np_acts-logits-general · gemini-2.0-flash

    superiority, prime, neo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ningar
    -0.52
    rzost
    -0.51
    ansvar
    -0.49
    estacks
    -0.48
    anao
    -0.45
    PX
    -0.45
    rateful
    -0.45
    杞
    -0.44
    taxes
    -0.44
    IMENTAL
    -0.44
    POSITIVE LOGITS
     assolu
    0.95
    rrggbb
    0.87
    Hentet
    0.84
     mundiales
    0.82
    tagHelperRunner
    0.78
    abestanden
    0.74
     status
    0.73
     absolue
    0.72
     absoluto
    0.72
     الحره
    0.69
    Act Density 0.245%

    No Known Activations