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

    Neuronpedia

    INDEX
    Explanations

    references to vacancies or empty spaces

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

    vacancy or vacant spaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Abp
    -0.29
     Vign
    -0.27
     الميل
    -0.26
    devtool
    -0.25
     quarter
    -0.24
     precisely
    -0.24
    riwal
    -0.23
     sitesinde
    -0.23
    Browsable
    -0.23
    digitalWrite
    -0.23
    POSITIVE LOGITS
     vacancy
    0.98
     vacancies
    0.89
     vacant
    0.86
     Vacant
    0.85
     gaps
    0.82
     Gaps
    0.82
    ImageContext
    0.80
     vacated
    0.75
     hueco
    0.73
     GAP
    0.73
    Act Density 0.122%

    No Known Activations