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

    Neuronpedia

    INDEX
    Explanations

    words that signify probability or likelihood

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

    adverb followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     creciendo
    -0.33
    的是
    -0.32
     crece
    -0.32
     láser
    -0.31
    Fue
    -0.31
     gobier
    -0.31
    getStart
    -0.31
     fanns
    -0.31
     ہیں
    -0.30
     pří
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.72
    Aholisi
    0.60
    ukkig
    0.58
    cipy
    0.57
     modulate
    0.55
    sätzlich
    0.55
    fromnode
    0.55
    akhstan
    0.54
     kaarangay
    0.54
    XtraBars
    0.54
    Act Density 0.076%

    No Known Activations