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

    Neuronpedia

    INDEX
    Explanations

    legal/financial terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     construit
    0.84
     MOSFET
    0.84
     CentOS
    0.82
     Hadoop
    0.81
     Metabol
    0.81
     应用
    0.80
     руха
    0.80
     streamwise
    0.80
     Nvidia
    0.77
    Installed
    0.77
    POSITIVE LOGITS
     уведом
    0.79
     khoản
    0.78
     schrift
    0.76
     forfait
    0.75
     povinn
    0.73
     délai
    0.70
     reimbursement
    0.70
     §
    0.68
     wajib
    0.68
     domicili
    0.67
    Act Density 0.075%

    No Known Activations