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

    Neuronpedia

    INDEX
    Explanations

    explain concepts related to different topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Initially
    0.53
    acción
    0.50
    a
    0.47
     Nothing
    0.44
     rápidos
    0.43
     dígitos
    0.43
    اد
    0.42
    adar
    0.42
    أ
    0.42
    s
    0.42
    POSITIVE LOGITS
    产量
    0.47
    纳
    0.45
     التيار
    0.43
     혹
    0.43
    मध्य
    0.43
    甫
    0.42
    的态度
    0.42
     ключе
    0.42
     사례
    0.42
     പ്രധാന
    0.41
    Act Density 0.000%

    No Known Activations