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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating personal experiences or opinions

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

    Past tense verbs followed by adverbs

    np_acts-logits-general · gemini-2.0-flash

    verb and its result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esternos
    -0.57
    izr
    -0.56
    GOTREF
    -0.56
    +#+#
    -0.56
     tersebut
    -0.55
    <sup>
    -0.54
     namelijk
    -0.53
    copyWith
    -0.53
    UIControlState
    -0.52
    ollectionView
    -0.52
    POSITIVE LOGITS
     ModelExpression
    0.66
     lotta
    0.62
     gotta
    0.62
    Šaltiniai
    0.58
     nope
    0.56
     myself
    0.56
    曖昧さ回避
    0.54
     uſed
    0.53
     same
    0.53
     lots
    0.52
    Act Density 0.130%

    No Known Activations