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

    Neuronpedia

    INDEX
    Explanations

    personal possessions and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kehidupan
    0.99
     personalidade
    0.98
    സ്വ
    0.96
     personnalité
    0.95
     personalidad
    0.94
     hobbies
    0.89
    jelen
    0.89
    abilidades
    0.87
    レクトリ
    0.86
    obbies
    0.86
    POSITIVE LOGITS
     colleague
    0.98
     colleagues
    0.91
     guests
    0.81
     intervention
    0.78
     suspicions
    0.77
     investigation
    0.76
     efforts
    0.74
     calculation
    0.72
    ক্ষেপে
    0.71
     scrutiny
    0.70
    Act Density 0.116%

    No Known Activations