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

    Neuronpedia

    INDEX
    Explanations

    numerical data related to percentages and statistical comparisons

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

    ranks and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    principalTable
    -0.49
    はじめに
    -0.46
    RegressionTest
    -0.43
    __':
    -0.42
    Ehrungen
    -0.42
    laştır
    -0.42
     Infórmanos
    -0.42
    QPushButton
    -0.41
    istoitu
    -0.41
    hyrchwyd
    -0.40
    POSITIVE LOGITS
     whopping
    0.59
     surpassing
    0.53
     ranked
    0.51
     rank
    0.51
     followed
    0.51
     Followed
    0.50
     ranking
    0.50
    followed
    0.49
    Followed
    0.49
    rank
    0.48
    Act Density 0.069%

    No Known Activations