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

    Neuronpedia

    INDEX
    Explanations

    damage and soreness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Notepad
    0.50
    밂
    0.48
     Officials
    0.48
     Vote
    0.48
     Brochure
    0.47
     Moe
    0.46
     Announced
    0.46
    Officials
    0.46
    ఓ
    0.46
     APRIL
    0.46
    POSITIVE LOGITS
    destroyed
    0.52
     archae
    0.51
     destroyed
    0.50
    in
    0.49
    exported
    0.48
    consumed
    0.48
     human
    0.48
     plunder
    0.47
     prehistoric
    0.47
    ancient
    0.46
    Act Density 0.009%

    No Known Activations