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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    terminus
    0.57
    vergne
    0.55
    ってた
    0.54
    assertTrue
    0.53
    последствии
    0.52
    っていた
    0.52
    lamide
    0.52
    pageY
    0.51
    notin
    0.51
     впоследствии
    0.51
    POSITIVE LOGITS
     here
    5.54
     Here
    5.10
    Here
    4.90
    here
    4.37
     aquí
    4.30
     HERE
    4.20
     aqui
    4.10
     здесь
    3.96
     এখানে
    3.66
    HERE
    3.64
    Act Density 1.816%

    No Known Activations