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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and references to relationships in sentences

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

    "and" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    mention of two people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     saurait
    -0.48
    toMatchSnapshot
    -0.46
     pinulongan
    -0.44
    definecolor
    -0.41
     sites
    -0.41
     financieras
    -0.39
     Wund
    -0.39
     místa
    -0.38
    ništ
    -0.36
     isn
    -0.36
    POSITIVE LOGITS
     Junto
    0.52
     Bersama
    0.52
     teammates
    0.52
    他和
    0.52
    junto
    0.52
    principalTable
    0.51
     colleagues
    0.51
    Transcripción
    0.50
    Климаты
    0.50
    Transkript
    0.50
    Act Density 0.318%

    No Known Activations