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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to computing, AI, and data processing

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

    following adjectives or adverbs

    np_acts-logits-general · gemini-2.0-flash

    common descriptive situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )";
    -0.95
     déchir
    -0.93
     boî
    -0.90
     vérit
    -0.89
    berdayakan
    -0.88
     noastră
    -0.85
     uș
    -0.82
    .)}
    -0.81
     auroit
    -0.81
     étoit
    -0.80
    POSITIVE LOGITS
     Nowadays
    1.00
     nowadays
    0.96
    Nowadays
    0.96
     oxigen
    0.86
     advices
    0.83
     viceversa
    0.82
    ´
    0.81
    lenght
    0.80
     «
    0.76
     cristal
    0.74
    Act Density 4.672%

    No Known Activations