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

    Neuronpedia

    INDEX
    Explanations

    nonprofit cloud

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ideological
    0.39
     brutality
    0.35
    過程中
    0.35
     ide
    0.34
     dissolved
    0.34
     είχε
    0.34
     Bols
    0.34
     propulsion
    0.34
    ポンプ
    0.34
     sacrific
    0.33
    POSITIVE LOGITS
    நி
    0.46
    gramModel
    0.45
     Networks
    0.41
    ము
    0.41
     Network
    0.40
    মতী
    0.40
    贞
    0.39
     jīn
    0.38
    
    0.38
    कारी
    0.38
    Act Density 0.000%

    No Known Activations