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

    Neuronpedia

    INDEX
    Explanations

    suggestions or recommendations for improvement or optimization

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

    Comparative and superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    Evaluations, comparisons, best options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    maxcdn
    -0.60
    lapsingToolbar
    -0.53
    kammer
    -0.48
    olarmente
    -0.47
     wireType
    -0.47
    cpus
    -0.46
     ordinaires
    -0.46
    lsb
    -0.46
    actéristique
    -0.46
    tabilis
    -0.46
    POSITIVE LOGITS
     better
    1.83
     best
    1.75
    better
    1.74
    Better
    1.60
     mejor
    1.54
     Better
    1.53
    best
    1.53
     лучше
    1.45
     melhor
    1.44
     meglio
    1.44
    Act Density 0.375%

    No Known Activations