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

    Neuronpedia

    INDEX
    Explanations

    specific characters or letters from various languages

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

    multilingual prefixes and questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Numerade
    -0.69
    ResumeLayout
    -0.52
     Biôgrafia
    -0.48
    -0.45
     Réponses
    -0.43
    ACHUSET
    -0.43
     EClass
    -0.41
    Vidite
    -0.41
    ſt
    -0.40
     huff
    -0.39
    POSITIVE LOGITS
    //
    0.52
     ***!
    0.48
    MADRID
    0.47
    0.46
    attutto
    0.45
    /**
    0.45
     iconLine
    0.44
    vains
    0.42
     oficina
    0.42
    simov
    0.42
    Act Density 0.052%

    No Known Activations