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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and structures, particularly in the context of functions or programming syntax

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

    numerical identifiers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     training
    -0.76
     trained
    -0.68
    Training
    -0.63
     Training
    -0.63
     neural
    -0.59
     train
    -0.56
    trained
    -0.56
     machine
    -0.56
    训练
    -0.55
     learning
    -0.54
    POSITIVE LOGITS
     Bioaccumulative
    0.43
     sprá
    0.40
     juridique
    0.38
     cocción
    0.37
     legais
    0.36
    WebControls
    0.36
     jurídico
    0.36
     animasi
    0.35
    ség
    0.35
     AssemblyTitle
    0.34
    Act Density 0.003%

    No Known Activations