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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash

    This neuron detects first‐person plural pronouns (e.g. “we,” “we’re,” “we’d”) indicating collective statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Bed
    -0.08
    _on
    -0.07
    Bars
    -0.07
    ▍▍
    -0.07
     погод
    -0.06
    しか
    -0.06
    "When
    -0.06
    omain
    -0.06
    amak
    -0.06
    Cars
    -0.06
    POSITIVE LOGITS
     Npgsql
    0.07
    -valu
    0.06
    แข
    0.06
    .scene
    0.06
     Ergebn
    0.06
     importing
    0.06
     रस
    0.06
    ФЛ
    0.06
    isk
    0.06
     punishing
    0.06
    Act Density 0.060%

    No Known Activations