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

    Neuronpedia

    INDEX
    Explanations

    samurai, loyalty, independence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     నిజ
    0.55
    绁
    0.53
     નક્કી
    0.53
    甕
    0.52
    िक्र
    0.51
     πολλ
    0.51
     loopholes
    0.50
    Unifier
    0.49
     ነገ
    0.49
     sasane
    0.49
    POSITIVE LOGITS
     was
    0.57
     at
    0.54
     di
    0.48
    0.47
     of
    0.46
     IS
    0.43
    IS
    0.43
     since
    0.42
     April
    0.41
     May
    0.41
    Act Density 0.004%

    No Known Activations