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

    Neuronpedia

    INDEX
    Explanations

    ask questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.64
    4
    0.63
    2
    0.61
    6
    0.57
    3
    0.57
    5
    0.53
    7
    0.51
    .
    0.48
     him
    0.47
    9
    0.46
    POSITIVE LOGITS
     রূপে
    0.55
    ᱶ
    0.45
    🚈
    0.44
     pavattati
    0.44
    缛
    0.44
    ᱙
    0.43
    ímenes
    0.42
    kho
    0.42
    OnFileChange
    0.42
    រួម
    0.42
    Act Density 0.001%

    No Known Activations