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

    Neuronpedia

    INDEX
    Explanations

    sentences and phrases that indicate conclusions, summaries, or results in a text

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

    statement in a section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.62
     ujednoznacz
    -0.59
    makeConstraints
    -0.56
    ፩
    -0.51
    niſſe
    -0.51
     ſind
    -0.51
    AndEndTag
    -0.50
    WebElementEntity
    -0.49
     himo
    -0.48
     nakalista
    -0.48
    POSITIVE LOGITS
    WarningLevel
    0.45
     فريبيس
    0.38
     makl
    0.34
    Tē
    0.33
    consulté
    0.32
    isNullOrEmpty
    0.30
     knock
    0.30
    fontawesome
    0.30
    ta
    0.29
    amerikanischer
    0.29
    Act Density 0.034%

    No Known Activations