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

    Neuronpedia

    INDEX
    Explanations

    operating manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nappropriate
    -1.00
    Roles
    -0.99
    Images
    -0.96
     التواصل
    -0.96
    Mega
    -0.94
     deploying
    -0.93
     modifié
    -0.93
    ština
    -0.92
     underval
    -0.92
    mega
    -0.92
    POSITIVE LOGITS
     sten
    1.02
     questionnaire
    0.96
     problems
    0.92
     Unesco
    0.90
     salesmen
    0.88
     questionnaires
    0.85
     sales
    0.84
     hospitalization
    0.83
     negro
    0.83
    检查
    0.82
    Act Density 0.053%

    No Known Activations