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

    Neuronpedia

    INDEX
    Explanations

    exclusive brand experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䳕
    0.48
    baiki
    0.48
     பொதுவாக
    0.46
     discontinuous
    0.46
    约束
    0.46
     generalmente
    0.45
     geralmente
    0.45
    莠
    0.45
     えっと
    0.45
     مسئلہ
    0.44
    POSITIVE LOGITS
     exclusive
    1.05
     exclusiva
    0.95
    exclusive
    0.93
     exclusivo
    0.92
     exclusivos
    0.91
    专属
    0.87
     exclusives
    0.86
    Exclusive
    0.84
     Exclusive
    0.80
     esclus
    0.79
    Act Density 0.009%

    No Known Activations