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

    Neuronpedia

    INDEX
    Explanations

    references and guidance related to legal or procedural frameworks

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

    guide, basis, reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     special
    -0.36
    awarkan
    -0.34
     beweging
    -0.33
     spezielle
    -0.33
     entregas
    -0.32
     jongen
    -0.32
    écriture
    -0.31
     spéciaux
    -0.31
     sogni
    -0.31
     sommeil
    -0.30
    POSITIVE LOGITS
     guide
    0.72
    bootstrapcdn
    0.65
     guides
    0.63
     BoxFit
    0.63
     guideline
    0.61
    guide
    0.60
    guided
    0.59
     basis
    0.57
     guía
    0.57
    参考
    0.57
    Act Density 0.237%

    No Known Activations