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

    Neuronpedia

    INDEX
    Explanations

    coding constructs and programming language syntax

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

    Code snippets or links

    np_acts-logits-general · gemini-2.0-flash

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ...
    -0.51
     Gil
    -0.48
    <<"\
    -0.47
     iVar
    -0.45
     …
    -0.45
     Ung
    -0.44
    hwar
    -0.44
    ieteur
    -0.44
     Ber
    -0.44
     â
    -0.43
    POSITIVE LOGITS
     Chengdu
    0.83
     feroit
    0.81
    saraba
    0.79
     WeChat
    0.78
     Hunan
    0.77
     relatifs
    0.73
     Sichuan
    0.73
     Shenzhen
    0.72
     Theſe
    0.72
     titolata
    0.71
    Act Density 0.322%

    No Known Activations