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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure elements

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

    Follows a period

    np_acts-logits-general · gemini-2.0-flash

    sentences about future outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    woordig
    -0.77
     pourtant
    -0.73
     AssemblyCulture
    -0.71
     récents
    -0.66
     AssemblyTitle
    -0.63
     recente
    -0.62
     récente
    -0.61
     senaste
    -0.61
    recent
    -0.60
     occurred
    -0.59
    POSITIVE LOGITS
     will
    1.50
     hopefully
    1.22
     nantinya
    1.22
     nanti
    1.19
    到时候
    1.19
    hopefully
    1.19
     Hopefully
    1.18
     będzie
    1.16
    Hopefully
    1.14
    will
    1.12
    Act Density 0.214%

    No Known Activations