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

    Neuronpedia

    INDEX
    Explanations

    terms related to reduction or elimination of taxes, practices, or harmful behaviors

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

    reduction or decrease

    np_acts-logits-general · gemini-2.0-flash

    reducing, decreasing, eliminating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SBATCH
    -0.64
    PreferredItem
    -0.61
    "]);
    -0.58
    /*
    -0.57
    "])
    -0.54
    ']){
    -0.54
     ]);
    -0.54
    "]];
    -0.53
    ('.');
    -0.53
    UVWXYZ
    -0.53
    POSITIVE LOGITS
     NSCoder
    0.64
    ValueStyle
    0.59
    imedia
    0.56
    NegativeButton
    0.53
    Sortie
    0.52
    COUVER
    0.51
    InjectAttribute
    0.51
     estekak
    0.51
    UnusedPrivate
    0.51
     než
    0.49
    Act Density 0.412%

    No Known Activations