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

    Neuronpedia

    INDEX
    Explanations

    for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    S
    0.47
    B
    0.41
    L
    0.40
    in
    0.39
    M
    0.38
    E
    0.36
     unter
    0.36
     aufge
    0.35
     সমস্ত
    0.35
     neues
    0.35
    POSITIVE LOGITS
     him
    0.64
     niego
    0.52
    them
    0.49
     us
    0.48
     them
    0.48
    你了
    0.47
     देम
    0.47
    هم
    0.45
     siebie
    0.44
     mình
    0.44
    Act Density 0.103%

    No Known Activations