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

    Neuronpedia

    INDEX
    Explanations

    structural analysis and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tpVar
    0.46
    अमेरिकी
    0.45
    वला
    0.42
    涿
    0.42
    局面
    0.42
    ")}}'
    0.42
    ⵜ
    0.42
    rainment
    0.42
    ὢ
    0.42
     colère
    0.41
    POSITIVE LOGITS
     steel
    0.55
     beam
    0.53
     brittle
    0.50
     flex
    0.48
     beams
    0.48
     Steel
    0.47
     micro
    0.46
     bridge
    0.46
     repair
    0.45
     calc
    0.45
    Act Density 0.025%

    No Known Activations