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

    Neuronpedia

    INDEX
    Explanations

    intellectual task that human

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     depth
    0.41
    Vinyl
    0.38
    плат
    0.37
    測
    0.37
    Dad
    0.36
    ponents
    0.36
    vinyl
    0.36
     distintas
    0.36
    心理
    0.36
    深度
    0.35
    POSITIVE LOGITS
     Metal
    0.62
     Metall
    0.56
     Slayer
    0.55
     Nuclear
    0.53
    Metal
    0.52
     NUCLEAR
    0.49
    METAL
    0.48
     Metals
    0.47
     핵
    0.47
     metals
    0.46
    Act Density 0.002%

    No Known Activations