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

    Neuronpedia

    INDEX
    Explanations

    pronouns and verbs indicating agency or necessity

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    conjunctions and discourse markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nochmals
    -0.57
     ytterligare
    -0.53
     Another
    -0.51
     هيا
    -0.51
    Another
    -0.51
     nochmal
    -0.51
     دیگری
    -0.51
     Paglinawan
    -0.51
     szint
    -0.50
     igen
    -0.50
    POSITIVE LOGITS
     bowiem
    0.96
     infatti
    0.80
     ведь
    0.80
    だって
    0.77
     totiž
    0.76
    awtextra
    0.76
     przecież
    0.75
    ypeł
    0.69
    󠁿
    0.69
     ergo
    0.67
    Act Density 0.298%

    No Known Activations