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

    Neuronpedia

    INDEX
    Explanations

    upper-case letters and the beginning of paragraphs

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

    Tokens preceding a sentence or clause

    np_acts-logits-general · gemini-2.0-flash

    sentence endings and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     démocr
    -0.65
    principalTable
    -0.59
    /**
    -0.59
    esgue
    -0.58
    aarrggbb
    -0.58
    initializeApp
    -0.56
     coloris
    -0.56
    évaluateur
    -0.56
     ExecuteAsync
    -0.54
     Cfr
    -0.54
    POSITIVE LOGITS
     Furthermore
    0.81
     Because
    0.80
    Because
    0.77
    Furthermore
    0.73
     The
    0.73
     In
    0.68
     Despite
    0.67
     Additionally
    0.65
     According
    0.63
     Although
    0.62
    Act Density 0.008%

    No Known Activations