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

    Neuronpedia

    INDEX
    Explanations

    larger in scope or size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mansions
    0.49
     kotak
    0.47
     continuamos
    0.45
     condos
    0.45
     mT
    0.44
     limitée
    0.44
     caixa
    0.44
     condominiums
    0.43
    ৩২
    0.43
     inability
    0.43
    POSITIVE LOGITS
    针对
    0.47
    ગાહી
    0.44
    -
    0.39
    本科
    0.39
    ‐
    0.39
    ärke
    0.38
    ället
    0.38
    Skippable
    0.38
     Web
    0.38
     देखते
    0.38
    Act Density 0.000%

    No Known Activations