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

    Neuronpedia

    INDEX
    Explanations

    Material Design guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mac
    0.95
    mac
    0.82
     Mac
    0.82
     Design
    0.73
    Mac
    0.73
     MAC
    0.72
     design
    0.68
    Design
    0.67
     macaroni
    0.65
    MAC
    0.65
    POSITIVE LOGITS
    芮
    0.42
    Aster
    0.38
     ശി
    0.38
     अजीत
    0.37
    緊
    0.36
    ळे
    0.36
    وامی
    0.36
    Khud
    0.36
     emitting
    0.35
    kých
    0.35
    Act Density 0.001%

    No Known Activations