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

    Neuronpedia

    INDEX
    Explanations

    ownership, not location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iniciativas
    0.49
    ⚭
    0.45
    藿
    0.43
    μφωνα
    0.42
     anticipates
    0.41
    佾
    0.41
     octombrie
    0.41
    MONTH
    0.41
     mentors
    0.40
     sequester
    0.40
    POSITIVE LOGITS
    简单的
    0.41
    ，
    0.40
     Graphics
    0.39
    의
    0.38
    の
    0.38
     graphics
    0.38
    れの
    0.38
    ของ
    0.37
    ஸின்
    0.37
     Shoes
    0.37
    Act Density 0.007%

    No Known Activations