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

    Neuronpedia

    INDEX
    Explanations

    company names and machinery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     worldview
    0.96
     freshmen
    0.82
     freshman
    0.81
     citizen
    0.76
     brazen
    0.75
     audacious
    0.75
     adım
    0.75
     demeanor
    0.75
     honored
    0.73
     purview
    0.72
    POSITIVE LOGITS
    Whilst
    1.12
     Whilst
    1.07
    Maintenance
    1.07
     HMRC
    0.97
    Replacement
    0.96
    Machines
    0.94
     forklift
    0.93
     Tractor
    0.92
     Machinery
    0.92
     двигателя
    0.92
    Act Density 0.001%

    No Known Activations