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

    Neuronpedia

    INDEX
    Explanations

    actions, decisions, and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Modeling
    0.33
     কেমন
    0.33
    were
    0.32
    with
    0.32
     možnost
    0.32
     medži
    0.32
    Monitoring
    0.32
    ம
    0.32
    Motivation
    0.31
     Variability
    0.31
    POSITIVE LOGITS
     sure
    0.86
     amends
    0.80
     inroads
    0.70
     decisions
    0.68
     adjustments
    0.64
     mistakes
    0.63
     assumptions
    0.61
     headway
    0.61
     predictions
    0.60
     landfall
    0.60
    Act Density 0.062%

    No Known Activations