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

    Neuronpedia

    INDEX
    Explanations

    dependency groupId or rel attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    zić
    0.77
    abord
    0.72
    áln
    0.66
    define
    0.66
    ći
    0.65
    cić
    0.64
    ão
    0.63
    Ć
    0.63
     வரைய
    0.63
    nh
    0.62
    POSITIVE LOGITS
     backlash
    0.73
     drawbacks
    0.70
     obstacles
    0.69
     raining
    0.68
     wasps
    0.65
     wastage
    0.65
     golpes
    0.64
     နောက်
    0.64
     warts
    0.64
     বাজে
    0.64
    Act Density 0.006%

    No Known Activations