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

    Neuronpedia

    INDEX
    Explanations

    containers for holding things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Strecke
    0.79
    oward
    0.77
    ாலிக
    0.75
    ков
    0.74
     createFile
    0.73
    র্ঘ
    0.70
     amplitud
    0.69
     immobilization
    0.68
    াব
    0.68
     streng
    0.66
    POSITIVE LOGITS
     đựng
    0.99
     containing
    0.87
     CONTAINER
    0.86
    Filled
    0.85
     chứa
    0.85
     cơm
    0.80
     berisi
    0.80
     EMPTY
    0.80
     filled
    0.78
     container
    0.77
    Act Density 0.107%

    No Known Activations