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

    Neuronpedia

    INDEX
    Explanations

    references and parameters related to web links and data attributes in coding contexts

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

    referral links and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -0.96
     للاسماء
    -0.91
    enablog
    -0.87
    ſelves
    -0.82
     ſche
    -0.81
     CreateTagHelper
    -0.79
    yntaxException
    -0.79
     fashiola
    -0.78
     pleaſure
    -0.78
    niſſe
    -0.77
    POSITIVE LOGITS
     refer
    0.42
     referido
    0.39
     reference
    0.38
     Referenzen
    0.37
    Reference
    0.36
     REFERENCE
    0.34
     referring
    0.33
     referencia
    0.33
     Refer
    0.33
     refers
    0.32
    Act Density 0.190%

    No Known Activations