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

    Neuronpedia

    INDEX
    Explanations

    instances of quoted speech and attribution in text

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

    verbs of reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.73
    Portale
    -0.65
     Италијани
    -0.57
    principalColumn
    -0.55
     autorytatywna
    -0.54
    ⟬
    -0.53
    rungsseite
    -0.52
     pinulongan
    -0.51
    UnitTesting
    -0.51
     كومونز
    -0.50
    POSITIVE LOGITS
     officials
    0.46
     announced
    0.39
     Offizielle
    0.37
     explained
    0.37
    Officials
    0.36
     açık
    0.36
     operar
    0.36
     menjelaskan
    0.36
    bootstrapcdn
    0.35
     attended
    0.35
    Act Density 0.182%

    No Known Activations