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

    Neuronpedia

    INDEX
    Explanations

    jurisdiction

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     トート
    0.62
    ючись
    0.58
     Lien
    0.56
    淤
    0.55
    incre
    0.54
     அதன்
    0.54
    Dragged
    0.54
     주고
    0.53
     Einen
    0.53
    楨
    0.53
    POSITIVE LOGITS
     entirety
    0.72
     warrantless
    0.70
     rulemaking
    0.67
     newest
    0.65
     entire
    0.63
     facility
    0.61
     rankings
    0.61
     qualification
    0.60
     recitation
    0.59
     Virginia
    0.59
    Act Density 0.001%

    No Known Activations