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

    Neuronpedia

    INDEX
    Explanations

    resource and memory usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jornadas
    0.69
    hnung
    0.69
     மெட்ரோ
    0.67
     straight
    0.66
    全市
    0.66
     éviter
    0.65
    諭
    0.65
     aven
    0.65
     Rana
    0.65
     jorn
    0.65
    POSITIVE LOGITS
     resource
    1.16
     Resource
    1.06
    Resource
    1.00
    resource
    0.93
    占
    0.84
    资源
    0.84
     resources
    0.84
    memory
    0.80
     차지
    0.80
     memory
    0.79
    Act Density 0.280%

    No Known Activations