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

    Neuronpedia

    INDEX
    Explanations

    scientific names and classifications of living organisms

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

    scientific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.66
     ſche
    -0.64
    tagHelper
    -0.60
     juſ
    -0.58
     pleaſure
    -0.57
     ſta
    -0.56
    WriteBarrier
    -0.56
     ſte
    -0.56
     anſ
    -0.54
     raiſ
    -0.54
    POSITIVE LOGITS
     Burch
    0.45
    gidos
    0.41
     noiva
    0.40
    ፩
    0.37
     arcilla
    0.36
    keta
    0.35
     Buren
    0.35
    這邊
    0.35
     ricordare
    0.35
    üyada
    0.35
    Act Density 0.023%

    No Known Activations