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

    Neuronpedia

    INDEX
    Explanations

    describing a state or identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '.
    0.63
    .
    0.63
    '
    0.62
     này
    0.58
     tomto
    0.55
    ;
    0.54
    .\"
    0.53
    นี้
    0.52
     this
    0.51
     이는
    0.50
    POSITIVE LOGITS
     një
    0.61
     μια
    0.60
     foundational
    0.60
     ஒரு
    0.59
     ചോദ്യ
    0.59
     ಅವಕಾಶ
    0.59
    ătur
    0.57
    ничный
    0.56
    ذج
    0.55
     isang
    0.55
    Act Density 0.020%

    No Known Activations