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

    Neuronpedia

    INDEX
    Explanations

    how to make decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.54
    erian
    0.53
    exclusion
    0.51
    🚻
    0.50
    erende
    0.49
    eras
    0.48
    furn
    0.47
    排除
    0.46
    adhesive
    0.46
    LaunchScheme
    0.46
    POSITIVE LOGITS
     nj
    0.52
     logo
    0.49
     FOUND
    0.47
     hydrogen
    0.47
    İN
    0.46
     температура
    0.46
     Talia
    0.46
     decision
    0.45
     Đ
    0.45
     fotoğraf
    0.45
    Act Density 0.001%

    No Known Activations