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

    Neuronpedia

    INDEX
    Explanations

    describing states or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Asimismo
    0.56
    avgsalary
    0.47
    Nếu
    0.45
     oftentimes
    0.43
     butadiene
    0.43
    Although
    0.42
     derivations
    0.42
    Otro
    0.42
    Adresse
    0.41
    Additionally
    0.41
    POSITIVE LOGITS
     Role
    0.95
     Function
    0.95
     Approach
    0.93
     Dis
    0.91
     Process
    0.91
     Support
    0.90
     History
    0.89
     Context
    0.89
     Purpose
    0.89
     Impact
    0.88
    Act Density 2.268%

    No Known Activations