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

    Neuronpedia

    INDEX
    Explanations

    references to the speaker's experiences or actions

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

    First-person pronouns followed by verbs in other languages

    np_acts-logits-general · gemini-2.0-flash

    me deciding, venturing, serving

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #+#
    -0.49
    ReusableCell
    -0.48
    mium
    -0.47
    esterno
    -0.47
     Gleichzeitig
    -0.47
    rechnung
    -0.47
    AddHtmlAttribute
    -0.47
     Esau
    -0.46
    dimethy
    -0.46
     Tada
    -0.45
    POSITIVE LOGITS
     convince
    0.54
     Consultado
    0.50
    存于互联网档案馆
    0.49
    ionado
    0.47
    strix
    0.47
     Encourage
    0.46
    pyplot
    0.46
     gustaría
    0.45
    phile
    0.45
    óricas
    0.44
    Act Density 0.046%

    No Known Activations