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

    Neuronpedia

    INDEX
    Explanations

    Mary

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Frozen
    0.74
     Soul
    0.69
     প্রাক্তন
    0.68
     DISABLED
    0.68
     frozen
    0.67
    arme
    0.65
     froze
    0.64
     છો
    0.64
    Frozen
    0.63
    ocop
    0.62
    POSITIVE LOGITS
     світі
    0.75
     świat
    0.67
     zdravot
    0.67
     ఆరోగ్య
    0.64
     Magdalene
    0.64
     دنیا
    0.62
     सेहत
    0.62
     wereld
    0.62
     rie
    0.61
     új
    0.61
    Act Density 0.002%

    No Known Activations