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

    Neuronpedia

    INDEX
    Explanations

    location or job details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Aloe
    0.44
    Aloe
    0.42
     सैलरी
    0.40
     salaries
    0.38
    xssf
    0.37
    verband
    0.36
     बढ़ा
    0.35
    薪
    0.35
    Salary
    0.34
     répertoire
    0.34
    POSITIVE LOGITS
    chn
    0.38
    inaire
    0.37
     han
    0.36
     svil
    0.36
    amese
    0.36
    qd
    0.35
     hanger
    0.35
    ondissement
    0.35
     വൈദ്യ
    0.35
    kurat
    0.35
    Act Density 0.005%

    No Known Activations