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

    Neuronpedia

    INDEX
    Explanations

    knowledge cutoff

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    人
    0.46
    も
    0.46
    도
    0.43
    生成
    0.42
    而
    0.42
    以及
    0.40
    共同
    0.40
    以下
    0.40
    笔
    0.40
    人群
    0.40
    POSITIVE LOGITS
     elektrische
    0.64
     gripe
    0.56
     ojo
    0.55
     telefone
    0.50
     alumina
    0.50
     nacht
    0.50
     naphthalene
    0.50
    oled
    0.48
     dielectric
    0.48
     electrónico
    0.48
    Act Density 0.001%

    No Known Activations