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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dosage and toxicity in medical contexts

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

    experimental data and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.63
    IndentedString
    -0.56
     الرياضيه
    -0.52
     FormBuilder
    -0.50
    叶凌天
    -0.47
     ModelExpression
    -0.47
     betweenstory
    -0.46
    Mab
    -0.46
    idopsis
    -0.45
    ✎
    -0.45
    POSITIVE LOGITS
    ManyToMany
    0.45
    ∬
    0.40
     Annan
    0.39
     Hoon
    0.38
    sstream
    0.38
    NN
    0.38
    noon
    0.37
    ning
    0.37
    hoog
    0.37
    acirc
    0.37
    Act Density 0.103%

    No Known Activations