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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and choices

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

    preceding imperative verbs

    np_acts-logits-general · gemini-2.0-flash

    modal verbs followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ynb
    -0.75
    AccessorTable
    -0.60
    invokeLater
    -0.59
    Separated
    -0.56
    ,‎
    -0.55
    enumii
    -0.55
    :])
    -0.54
    WindowListener
    -0.53
    MLLoader
    -0.52
    Giving
    -0.52
    POSITIVE LOGITS
     бъдат
    0.56
     behold
    0.55
    +#+#
    0.52
     master
    0.51
    Билгалдахарш
    0.51
    wnątrz
    0.51
     Behold
    0.50
    lüssel
    0.49
     cui
    0.49
    parseFrom
    0.48
    Act Density 0.229%

    No Known Activations