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

    Neuronpedia

    INDEX
    Explanations

    size, state, or qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Start
    0.31
    Collection
    0.31
    Merge
    0.30
    Ammo
    0.30
     Алла
    0.30
    Analyze
    0.30
    Calculation
    0.30
    Erro
    0.29
    Lecture
    0.29
    Tournament
    0.29
    POSITIVE LOGITS
     magazines
    0.36
    nesses
    0.35
     populations
    0.34
     versions
    0.34
     environments
    0.34
     ones
    0.33
     geographies
    0.32
     deployments
    0.32
     periodicals
    0.32
     societies
    0.31
    Act Density 0.486%

    No Known Activations