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

    Neuronpedia

    INDEX
    Explanations

    documents and installations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unmarked
    0.56
    ત્મક
    0.55
    म्मे
    0.54
    ಶ್ಚ
    0.54
     실제
    0.54
     에너지
    0.52
     آد
    0.50
     메소
    0.50
    <unused2113>
    0.50
     oblast
    0.49
    POSITIVE LOGITS
    com
    0.47
    有
    0.43
    がある
    0.42
     teste
    0.42
    =
    0.41
     sou
    0.40
    不利
    0.40
     The
    0.40
    即可
    0.39
    公式
    0.39
    Act Density 0.002%

    No Known Activations