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

    Neuronpedia

    INDEX
    Explanations

    relating to others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avem
    0.33
    各大
    0.32
     spezif
    0.30
     "|"
    0.30
     FormsModule
    0.29
     pentru
    0.29
     beiden
    0.29
     abbiamo
    0.29
     средств
    0.29
    seits
    0.29
    POSITIVE LOGITS
     fellow
    0.61
     others
    0.58
     strangers
    0.58
    别人
    0.58
    他人
    0.58
     लोगों
    0.57
     사람
    0.57
    其他人
    0.57
     people
    0.52
     pessoas
    0.52
    Act Density 0.208%

    No Known Activations