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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making decisions and managing processes

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

    Followed by indefinite or definite articles

    np_acts-logits-general · gemini-2.0-flash

    action verbs followed by articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.75
    ,
    -0.51
    ?
    -0.47
     and
    -0.44
    ;
    -0.43
     or
    -0.41
    ↵↵
    -0.41
     
    -0.40
    ↵
    -0.40
     When
    -0.39
    POSITIVE LOGITS
     صوتيه
    1.00
     Мексичка
    0.95
    TagMode
    0.91
     propOrder
    0.90
     pleaſure
    0.89
    AccessorTable
    0.89
    __(/*!
    0.88
     ſtate
    0.88
    IntOverflow
    0.88
     ſta
    0.85
    Act Density 0.563%

    No Known Activations