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

    Neuronpedia

    INDEX
    Explanations

    mentions of plugins and their related terminology

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

    plugin for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Heere
    -0.51
     noqa
    -0.41
     voici
    -0.40
     stara
    -0.38
     relâche
    -0.38
     skut
    -0.36
    atguigu
    -0.36
     Số
    -0.36
     temperaturas
    -0.35
     Voici
    -0.35
    POSITIVE LOGITS
     plugin
    2.05
     Plugin
    1.93
    plugin
    1.86
     plugins
    1.84
    Plugin
    1.78
     Plugins
    1.74
    Plugins
    1.56
     PLUG
    1.54
    lugin
    1.49
     plug
    1.47
    Act Density 0.009%

    No Known Activations