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

    Neuronpedia

    INDEX
    Explanations

    crisis helplines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lex
    0.70
    Rent
    0.70
     continúa
    0.69
     किशन
    0.69
     constituyen
    0.67
     rent
    0.65
     continue
    0.65
     lash
    0.65
     진
    0.64
     lanza
    0.62
    POSITIVE LOGITS
     Soldier
    0.66
    海道
    0.61
    Cumm
    0.57
    rophys
    0.55
    ௐ
    0.55
     sediments
    0.54
     Problems
    0.54
    пон
    0.54
     Comput
    0.54
     মরি
    0.53
    Act Density 0.193%

    No Known Activations