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

    Neuronpedia

    INDEX
    Explanations

    events and entertainment

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ifica
    0.72
    Charm
    0.72
    redd
    0.72
    tedir
    0.72
    lash
    0.72
     놓고
    0.71
     summarize
    0.71
    Cont
    0.71
    antan
    0.70
    ressive
    0.70
    POSITIVE LOGITS
     فو
    0.75
     theater
    0.74
     Geschäft
    0.73
     abras
    0.72
     wom
    0.72
    蓄
    0.70
     theatre
    0.69
     Lazarus
    0.69
     Thé
    0.69
     Theater
    0.69
    Act Density 0.002%

    No Known Activations