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

    Neuronpedia

    INDEX
    Explanations

    relationships, situations, life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ng
    0.41
    ucco
    0.41
     additional
    0.41
     WERE
    0.40
     L
    0.40
    ft
    0.40
    net
    0.40
    storage
    0.40
    anti
    0.39
     Com
    0.39
    POSITIVE LOGITS
     విషయంలో
    0.59
    对待
    0.57
     parenting
    0.56
     인생
    0.54
    삶
    0.53
     삶
    0.51
     biznes
    0.50
     свадь
    0.50
     metaphor
    0.49
    ชีวิต
    0.49
    Act Density 0.215%

    No Known Activations