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

    Neuronpedia

    INDEX
    Explanations

    understand your approach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    0.46
    uset
    0.46
    that
    0.46
    owner
    0.46
     hundred
    0.45
    ].[
    0.44
     If
    0.43
    op
    0.42
    티
    0.42
    🎷
    0.42
    POSITIVE LOGITS
     accumulates
    0.49
     台
    0.49
     convivencia
    0.49
     показателей
    0.46
    ຢ່າງ
    0.45
    ອບ
    0.43
     indoct
    0.41
    Չ
    0.41
    ່າຍ
    0.41
     संकट
    0.40
    Act Density 0.001%

    No Known Activations