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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and references to moral or philosophical concepts

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

    self or others in contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.67
    StoryboardSegue
    -0.65
    SuppressLint
    -0.64
    .*")]
    -0.63
     zwiſchen
    -0.61
    apimachinery
    -0.60
    RegistryLite
    -0.59
    OGND
    -0.59
     propOrder
    -0.59
     témoig
    -0.58
    POSITIVE LOGITS
     móvel
    0.36
    으
    0.36
    Cyfarwyddwr
    0.31
     empfohlen
    0.29
     Wirksamkeit
    0.29
     متعلقه
    0.28
     heißen
    0.28
     Öffentlichkeit
    0.28
     Handlung
    0.28
     Vernunft
    0.28
    Act Density 0.309%

    No Known Activations