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

    Neuronpedia

    INDEX
    Explanations

    descriptions of uniqueness and distinction

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

    Comparative or superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    comparative and superlative adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IndexPath
    -0.58
    bootstrapcdn
    -0.55
    fjspx
    -0.55
     defaultstate
    -0.54
    PerformLayout
    -0.54
     Monfieur
    -0.50
    chitis
    -0.50
    JNIEnv
    -0.50
    CppMethod
    -0.50
    EDEFAULT
    -0.50
    POSITIVE LOGITS
     nor
    0.86
    RegressionTest
    0.77
     better
    0.73
     truer
    0.69
     happier
    0.66
     sweeter
    0.66
     finer
    0.66
    nor
    0.65
     more
    0.63
    better
    0.63
    Act Density 0.069%

    No Known Activations