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

    Neuronpedia

    INDEX
    Explanations

    challenging expectations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     katalog
    0.52
     ungg
    0.48
     partenza
    0.47
     kriter
    0.45
     pelaksanaan
    0.45
     distribuzione
    0.44
     player
    0.42
     speelt
    0.42
     scenario
    0.42
     frost
    0.42
    POSITIVE LOGITS
    nds
    0.49
    ly
    0.48
    ious
    0.46
    undaria
    0.46
     வீட்டில்
    0.45
    ５
    0.45
     effortlessly
    0.45
     THEN
    0.44
     そこ
    0.44
     販売
    0.44
    Act Density 0.002%

    No Known Activations