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

    Neuronpedia

    INDEX
    Explanations

    confidentiality and disclaimers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     recense
    0.47
    召唤
    0.46
     რამდ
    0.42
     구독
    0.41
     extracción
    0.40
     carro
    0.40
     vasomotor
    0.40
     claus
    0.39
    סק
    0.39
     পত্রিকা
    0.39
    POSITIVE LOGITS
     confidential
    0.57
     company
    0.48
     confidentiality
    0.47
     Company
    0.47
     electronically
    0.46
     Confidential
    0.45
    company
    0.44
     KPMG
    0.44
     employees
    0.43
    Company
    0.43
    Act Density 0.025%

    No Known Activations